Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 14432
    Prev
    Next
    INDEX
    Explanations

    references to specific methods and procedures in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reafon
    -0.66
    pośred
    -0.65
     NDEBUG
    -0.65
    etheless
    -0.65
    intenance
    -0.62
     Chrift
    -0.62
    úrese
    -0.62
     reaſon
    -0.61
    berdayakan
    -0.61
    blauch
    -0.60
    POSITIVE LOGITS
    WebVitals
    0.79
    EndContext
    0.66
    Vidite
    0.60
    onders
    0.57
    Curious
    0.57
    до
    0.56
    AntiForgeryToken
    0.56
    $__
    0.55
    diğinde
    0.54
    to
    0.54
    Activations Density 0.021%

    No Known Activations