© 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. 20-CLT-HP
    7. 77062
    Prev
    Next
    INDEX
    Explanations

    code and programming discussions

    np_max-act-logits · 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
    findpost
    -0.59
    emplar
    -0.52
     pledge
    -0.51
     puits
    -0.50
    deauna
    -0.48
     pledges
    -0.47
    mybatisplus
    -0.47
    togram
    -0.47
    GraphicsUnit
    -0.46
     indemnity
    -0.46
    POSITIVE LOGITS
     AspNetCore
    0.61
    DataSnapshot
    0.57
    ContentAsync
    0.56
    Personendaten
    0.56
     arşivlendi
    0.54
    StoreMessageInfo
    0.54
    RefreshLayout
    0.52
     Ause
    0.51
    rend
    0.50
     CiNii
    0.48
    Activations Density 0.000%

    No Known Activations