© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95487
    Prev
    Next
    INDEX
    Explanations

    historical events/research

    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
     funded
    -0.85
     Funded
    -0.83
     invaded
    -0.80
     Blow
    -0.74
    funded
    -0.73
    Blow
    -0.71
    Funded
    -0.71
     infiltrated
    -0.70
     blow
    -0.69
    blow
    -0.68
    POSITIVE LOGITS
    Geplaatst
    0.58
    DoubleQuotes
    0.48
    tvguidetime
    0.48
    TRAILING
    0.47
    GOTREF
    0.47
    /*
    0.46
    REDIT
    0.46
    Alo
    0.45
    TableHead
    0.45
    bereit
    0.45
    Activations Density 0.434%

    No Known Activations