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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3598
    Prev
    Next
    INDEX
    Explanations

    the word "how" and phrases related to problem-solving and analysis

    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
    528
    +0.10
    0.3%
    1350
    +0.10
    0.3%
    68
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.10
    0.06
    68
    +0.10
    0.05
    1777
    +0.10
    0.05
    Negative Logits
     reluct
    -0.67
     gaily
    -0.61
     unspeak
    -0.60
     emphat
    -0.60
     languid
    -0.58
    AMILTON
    -0.57
     trö
    -0.57
     luxuriant
    -0.56
     perfet
    -0.56
     vété
    -0.56
    POSITIVE LOGITS
     how
    0.95
    how
    0.84
     HOW
    0.82
     How
    0.77
    How
    0.73
    HOW
    0.72
    šech
    0.55
    howto
    0.53
    
    0.50
     cómo
    0.50
    Activations Density 0.128%

    No Known Activations