© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    references to authorship and publication credit

    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
    تقاوى
    -0.76
    }{*}{
    -0.73
    ISupport
    -0.73
     MainAxisSize
    -0.73
    parsedMessage
    -0.73
    })));
    -0.70
    CloseOperation
    -0.70
    DoubleQuotes
    -0.69
    defineProperty
    -0.69
    ValueStyle
    -0.68
    POSITIVE LOGITS
    lexia
    0.62
    acyjna
    0.52
    щенный
    0.47
     AssemblyCompany
    0.46
     ultimatum
    0.46
    WebControls
    0.45
    なぜか
    0.45
    ÉE
    0.45
     createdAt
    0.44
    pania
    0.44
    Activations Density 0.002%

    No Known Activations