© 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. 95081
    Prev
    Next
    INDEX
    Explanations

    by

    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
    by
    -1.48
     W
    -1.45
    W
    -1.33
     
    -1.19
    j
    -1.01
    ,
    -0.99
     by
    -0.92
    ↵
    -0.90
    .
    -0.90
     (
    -0.86
    POSITIVE LOGITS
     itſelf
    2.00
     myſelf
    1.93
     raiſ
    1.80
    ^(@)
    1.70
     ་་
    1.70
     Monfieur
    1.70
    ſelf
    1.69
     Мексичка
    1.68
     iſt
    1.64
     Efq
    1.64
    Activations Density 0.865%

    No Known Activations