© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1706
    Prev
    Next
    INDEX
    Explanations

    Wall

    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
    mergeFrom
    -0.61
    DeleteBehavior
    -0.61
     <",
    -0.60
    awtextra
    -0.60
    DebuggerStep
    -0.59
    ArgsConstructor
    -0.57
    fillType
    -0.56
    EndInit
    -0.54
    OpenHelper
    -0.54
     kasarigan
    -0.54
    POSITIVE LOGITS
    izhou
    0.52
     portugu
    0.49
     potentiel
    0.48
     Proust
    0.48
     cytok
    0.47
     JSTOR
    0.47
     Rota
    0.47
    woff
    0.46
    nloa
    0.45
     Pizarro
    0.45
    Activations Density 0.002%

    No Known Activations