© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71632
    Prev
    Next
    INDEX
    Explanations

    surfaces

    np_max-act-logits · 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
     Ceinture
    -0.76
    parsedMessage
    -0.75
    RuleContext
    -0.73
    mtrl
    -0.71
     Exactos
    -0.70
    舺
    -0.68
    invokeLater
    -0.68
    featureID
    -0.66
    İstinadlar
    -0.66
    fields
    -0.65
    POSITIVE LOGITS
     surface
    0.66
    AnchorStyles
    0.44
    UrlResolution
    0.44
     SURFACE
    0.43
     Surface
    0.42
    surface
    0.39
    SuppressLint
    0.39
    #+#
    0.38
    aap
    0.37
    ัพท์
    0.37
    Activations Density 0.000%

    No Known Activations