© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 9408
    Prev
    Next
    INDEX
    Explanations

    engineering

    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
     resourceCulture
    -0.81
    Personensuche
    -0.80
    AndEndTag
    -0.72
    WireFormatLite
    -0.62
     Himo
    -0.60
    principalColumn
    -0.56
    OGND
    -0.54
    resave
    -0.53
    XmlAccessorType
    -0.52
    LookAnd
    -0.52
    POSITIVE LOGITS
    endgroup
    0.54
     hypocrite
    0.50
     هن
    0.50
     sadar
    0.50
     rien
    0.49
    getClassName
    0.49
    ಶ
    0.48
    ינ
    0.48
    ûte
    0.48
    deviantart
    0.47
    Activations Density 0.003%

    No Known Activations