© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 471
    Prev
    Next
    INDEX
    Explanations

    question answering context

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vance
    -0.68
    IsMutable
    -0.67
    қ
    -0.67
    gatsby
    -0.64
    ApiModelProperty
    -0.63
     Betts
    -0.63
    paksa
    -0.63
    s
    -0.62
     unknownFields
    -0.61
     Paz
    -0.61
    POSITIVE LOGITS
     where
    2.63
    where
    2.47
     Where
    2.28
    Where
    2.25
     WHERE
    2.20
    WHERE
    1.99
     donde
    1.82
     où
    1.72
    Donde
    1.72
    donde
    1.68
    Activations Density 0.667%

    No Known Activations