© 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. 92712
    Prev
    Next
    INDEX
    Explanations

    blooming

    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
    featureID
    -0.69
    rrggbb
    -0.68
    Personensuche
    -0.66
     وتسجيلات
    -0.64
    |};
    -0.64
    bootstrapcdn
    -0.63
     roulant
    -0.63
    spirit
    -0.63
     scolaires
    -0.61
     فريبيس
    -0.61
    POSITIVE LOGITS
    fgets
    0.43
     незавершена
    0.40
    BoxShadow
    0.39
    mailto
    0.39
    ::::::::
    0.39
     profeta
    0.38
    postdata
    0.38
    AddWithValue
    0.38
    URLException
    0.37
    esac
    0.36
    Activations Density 0.003%

    No Known Activations