© 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. 20-CLT-HP
    7. 77104
    Prev
    Next
    INDEX
    Explanations

    journal entries

    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
     jspb
    -0.73
     AssemblyCulture
    -0.71
    elemField
    -0.60
    aarrggbb
    -0.59
    +#+#
    -0.56
     @"/
    -0.56
    windowFixed
    -0.55
    LookAnd
    -0.54
    Kjelder
    -0.51
     BrowserModule
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    endimiento
    0.50
    AspNet
    0.47
    uestamente
    0.46
     diaries
    0.45
    zugehen
    0.45
     AssemblyVersion
    0.45
    άσ
    0.44
     Bols
    0.44
    lux
    0.44
    Activations Density 0.001%

    No Known Activations