© 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. 77665
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations

    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
     U
    -0.59
    aarrggbb
    -0.58
     ModelExpression
    -0.56
    dafx
    -0.54
    verwijspagina
    -0.54
    DataPropertyName
    -0.53
    govine
    -0.50
     EconPapers
    -0.49
    ResumeLayout
    -0.49
    autique
    -0.49
    POSITIVE LOGITS
    mS
    0.56
     שוליים
    0.55
    UST
    0.55
    ESM
    0.54
    USE
    0.54
    dS
    0.53
    usp
    0.52
    cS
    0.52
    USP
    0.52
    iesc
    0.50
    Activations Density 0.001%

    No Known Activations