© 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. 12151
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophical concepts and statements of truth

    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
    1363
    +0.14
    0.5%
    545
    +0.11
    0.4%
    1909
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.14
    0.03
    1363
    +0.11
    0.03
    545
    +0.10
    0.03
    Negative Logits
     kram
    -0.68
     augus
    -0.62
     katal
    -0.62
     nomine
    -0.61
     republi
    -0.60
     uhr
    -0.60
     pü
    -0.59
     hek
    -0.59
     makro
    -0.59
     tisch
    -0.59
    POSITIVE LOGITS
     truth
    1.11
     Truth
    1.06
    Truth
    1.06
     truths
    1.04
    truth
    1.03
     TRUTH
    1.01
     truthful
    0.76
     Truths
    0.73
     truthfully
    0.66
     heapq
    0.66
    Activations Density 0.062%

    No Known Activations