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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14694
    Prev
    Next
    INDEX
    Explanations

    error handling and exception-related terms

    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
     Wikimedijinoj
    -0.52
    setVerticalGroup
    -0.49
    oia
    -0.49
    än
    -0.47
     Mank
    -0.47
    UnsafeEnabled
    -0.47
    アド
    -0.46
    range
    -0.45
     kard
    -0.45
    ブログ
    -0.45
    POSITIVE LOGITS
     виправивши
    0.67
     tartalomajánló
    0.59
    الدراسه
    0.57
     TextAppearance
    0.57
    Rptr
    0.56
     Empieza
    0.56
     صوتيه
    0.56
    yargs
    0.55
    يكب
    0.55
    fseek
    0.53
    Activations Density 0.013%

    No Known Activations