© 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. 5-CLT-HP
    7. 3446
    Prev
    Next
    INDEX
    Explanations

    rabbit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.74
    ;->
    -0.47
    typeorm
    -0.46
    step
    -0.45
    extend
    -0.44
    lacing
    -0.44
    /*
    -0.42
     henvisninger
    -0.41
     idr
    -0.41
    leine
    -0.40
    POSITIVE LOGITS
    ArgsConstructor
    0.60
     poly
    0.58
    iastes
    0.57
    osoever
    0.56
     TextInputType
    0.56
    IsMutable
    0.53
     Trouver
    0.52
    AFTA
    0.52
     صوتيه
    0.51
     layui
    0.50
    Activations Density 0.008%

    No Known Activations