© 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. 91901
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    IndentedString
    -0.69
    Personendaten
    -0.68
    Diwedd
    -0.68
     صوتيه
    -0.62
    Autoritní
    -0.62
    Identyfik
    -0.58
    EndGlobalSection
    -0.58
    PreferredItem
    -0.57
    دانشنامهٔ
    -0.57
    WriteLiteral
    -0.56
    POSITIVE LOGITS
     cref
    0.65
    LikeLike
    0.52
    providedIn
    0.47
    achio
    0.47
    DOMAIN
    0.46
    nesty
    0.46
    raszam
    0.45
     창
    0.45
     *_
    0.45
    nahmen
    0.44
    Activations Density 0.007%

    No Known Activations