© 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. 9344
    Prev
    Next
    INDEX
    Explanations

    pouring

    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
     ModelExpression
    -0.50
    urbation
    -0.47
    ={`/
    -0.44
    ios
    -0.44
     كومونز
    -0.41
    minecraft
    -0.41
    is
    -0.41
    òng
    -0.41
    RequestMapping
    -0.41
    şiv
    -0.41
    POSITIVE LOGITS
    دانشنامهٔ
    0.86
    bewerken
    0.70
    RTEX
    0.67
    IndentedString
    0.66
    expandindo
    0.65
    Atsauces
    0.63
    landmark
    0.60
    انجليز
    0.60
    etcode
    0.60
    )++;
    0.59
    Activations Density 0.083%

    No Known Activations