© 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. 1-CLT-HP
    7. 15013
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

    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
    脚注の使い方
    -0.99
     ModelExpression
    -0.88
    setVerticalGroup
    -0.83
     CreateTagHelper
    -0.82
    ⓧ
    -0.79
    /**
    -0.76
    ene
    -0.66
    UnusedPrivate
    -0.66
     '\\;'
    -0.66
    twimg
    -0.65
    POSITIVE LOGITS
    tically
    0.56
    ven
    0.52
    vel
    0.50
    metic
    0.46
    queness
    0.45
    ament
    0.45
    ti
    0.45
    вига
    0.45
    ously
    0.44
    werk
    0.44
    Activations Density 0.022%

    No Known Activations