© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6785
    Prev
    Next
    INDEX
    Explanations

    phrases related to consistency and variance across texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    889
    +0.17
    0.6%
    573
    +0.14
    0.5%
    1306
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.17
    0.03
    889
    +0.14
    0.02
    1306
    +0.13
    0.03
    Negative Logits
     impra
    -0.88
     indestru
    -0.86
     inev
    -0.85
     inconce
    -0.83
     insuper
    -0.79
     excru
    -0.78
     reluct
    -0.77
     unspeak
    -0.77
     disagre
    -0.76
     affor
    -0.74
    POSITIVE LOGITS
     consistent
    1.10
     consistency
    1.09
    consistent
    0.95
     Consistency
    0.89
     inconsistent
    0.87
    Consistency
    0.84
     Consistent
    0.80
    Consistent
    0.78
     CONS
    0.75
    consistency
    0.74
    Activations Density 0.086%

    No Known Activations