© 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. 4-CLT-HP
    7. 2100
    Prev
    Next
    INDEX
    Explanations

    kan

    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
     Soria
    -0.47
     scurt
    -0.46
     JADX
    -0.46
     lyder
    -0.46
     paese
    -0.43
     quinto
    -0.42
     at
    -0.42
    ьаж
    -0.42
     utara
    -0.41
     minor
    -0.40
    POSITIVE LOGITS
    ban
    0.75
    bans
    0.73
    BAN
    0.71
    Ban
    0.70
    APAN
    0.65
     Cabot
    0.64
    PyExc
    0.62
     banning
    0.61
     BAN
    0.61
    apan
    0.60
    Activations Density 0.003%

    No Known Activations