© 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. 2-RES-MATRYOSHKA-DC
    7. 5805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "AFFIRMED" or similar affirming legal terminology

    oai_token-act-pair · gpt-4.1-nano
    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
    ')}}
    -0.62
    ']))
    -0.61
    enumi
    -0.60
    >")
    -0.59
    帖最后由
    -0.56
    UnsafeEnabled
    -0.55
    '])){
    -0.54
    iastical
    -0.53
    >";
    -0.52
    responseType
    -0.52
    POSITIVE LOGITS
    AFFIRMED
    5.25
    Affirmed
    2.55
     CURIAM
    0.69
     Bors
    0.67
    gatsby
    0.66
     isNameExpr
    0.63
    лактика
    0.60
    LookAnd
    0.60
    setPointSize
    0.59
    SOUNDBITE
    0.59
    Activations Density 0.001%

    No Known Activations