© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92932
    Prev
    Next
    INDEX
    Explanations

    others

    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
     nahilalakip
    -0.93
    BeginContext
    -0.92
    Viitteet
    -0.80
     perfons
    -0.75
     dafs
    -0.74
     pleaſure
    -0.73
     Jefus
    -0.71
    amoan
    -0.70
    esterday
    -0.69
     myſelf
    -0.69
    POSITIVE LOGITS
    .
    0.80
    ,
    0.66
    -
    0.39
    execSQL
    0.35
    <eos>
    0.32
     répar
    0.32
     landet
    0.31
     roulant
    0.31
     all
    0.30
     líquidos
    0.30
    Activations Density 0.005%

    No Known Activations