© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2367
    Prev
    Next
    INDEX
    Explanations

    one

    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
    IntoConstraints
    -0.92
     InputDecoration
    -0.91
    LLocation
    -0.85
    featureID
    -0.84
    extAlignment
    -0.82
    WriteTagHelper
    -0.81
    UrlResolution
    -0.79
    出版年
    -0.77
    styleType
    -0.74
    zzleHttp
    -0.73
    POSITIVE LOGITS
     only
    0.65
    ,
    0.54
     ONLY
    0.54
     Only
    0.53
     seulement
    0.53
    Only
    0.49
    terase
    0.49
     APPRO
    0.48
    only
    0.48
     apenas
    0.47
    Activations Density 0.006%

    No Known Activations