© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97288
    Prev
    Next
    INDEX
    Explanations

    grapes or silence

    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
     itſelf
    -1.45
     myſelf
    -1.43
     pleaſure
    -1.34
     Majefty
    -1.30
    ſelf
    -1.27
     Efq
    -1.26
     himſelf
    -1.23
     themſelves
    -1.23
     Anſ
    -1.23
    neſs
    -1.20
    POSITIVE LOGITS
     
    0.81
    ,
    0.77
     (
    0.75
     in
    0.71
     I
    0.69
    .
    0.66
    /
    0.66
     G
    0.66
    ↵↵
    0.63
     and
    0.61
    Activations Density 0.092%

    No Known Activations