© 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. 3771
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     Roskov
    -1.07
     nahilalakip
    -1.04
    LookAnd
    -1.02
    المشاركات
    -1.02
    adaptiveStyles
    -0.94
    parsedMessage
    -0.94
    thâu
    -0.94
    Personensuche
    -0.92
     autorytatywna
    -0.88
     AssemblyCulture
    -0.86
    POSITIVE LOGITS
    .
    0.58
    ्य
    0.47
     Bel
    0.46
    bel
    0.42
    /
    0.42
     Edwards
    0.42
     sp
    0.42
     bel
    0.41
    .(
    0.41
     in
    0.40
    Activations Density 0.064%

    No Known Activations