© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91682
    Prev
    Next
    INDEX
    Explanations

    Product/item identifiers

    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
     oreilles
    -0.42
    cella
    -0.40
     vœux
    -0.40
     rigue
    -0.40
    yntaxException
    -0.39
    mtext
    -0.39
     peccato
    -0.38
     arred
    -0.38
    jspx
    -0.38
    uidado
    -0.37
    POSITIVE LOGITS
    expandindo
    0.87
     onBind
    0.74
    ISupport
    0.72
     صوتيه
    0.71
    IonicModule
    0.70
    NSU
    0.68
     فريبيس
    0.67
     helicopters
    0.67
    VIAF
    0.64
    Obrázky
    0.64
    Activations Density 0.047%

    No Known Activations