© 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. 1780
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    curo
    -0.49
    *}$
    -0.49
    gå
    -0.47
    リコン
    -0.47
    出版年
    -0.47
    Demografia
    -0.47
     surla
    -0.46
    BAG
    -0.45
    جغرافيا
    -0.44
     Eck
    -0.44
    POSITIVE LOGITS
     виправивши
    0.74
     Which
    0.64
    Which
    0.59
    RTLR
    0.58
     Whom
    0.58
     préfé
    0.57
     getopt
    0.57
     whom
    0.56
    WithIdentifier
    0.56
     którzy
    0.55
    Activations Density 0.108%

    No Known Activations