© 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. 0-CLT-HP
    7. 43388
    Prev
    Next
    INDEX
    Explanations

    knowledge/understanding

    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
     mind
    -1.18
     Mind
    -0.96
    Mind
    -0.94
     minds
    -0.92
    mind
    -0.92
     MIND
    -0.89
     Reſ
    -0.75
     Anſ
    -0.68
    MIND
    -0.68
     Minds
    -0.67
    POSITIVE LOGITS
    <bos>
    0.69
    sidemargin
    0.68
     a
    0.55
     and
    0.48
    djangoproject
    0.48
    ,
    0.47
     فريبيس
    0.46
    AccessorTable
    0.46
     dàng
    0.46
    ed
    0.46
    Activations Density 0.556%

    No Known Activations