© 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. 4-CLT-HP
    7. 447
    Prev
    Next
    INDEX
    Explanations

    /

    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
     esternos
    -0.74
     ExecuteAsync
    -0.74
    ViewFeatures
    -0.67
    esModule
    -0.66
    stateProvider
    -0.66
    ReusableCell
    -0.65
     uintptr
    -0.60
    localctx
    -0.59
     typelib
    -0.59
    Autoritní
    -0.58
    POSITIVE LOGITS
    SequentialGroup
    0.50
     Chapelle
    0.48
    ళ
    0.46
     Arno
    0.44
    ma
    0.43
    XmlAccessType
    0.43
    agne
    0.43
     Ange
    0.42
    AppName
    0.42
    Kirche
    0.42
    Activations Density 0.026%

    No Known Activations