© 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. 1-CLT-HP
    7. 15576
    Prev
    Next
    INDEX
    Explanations

    aties

    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
    OGND
    -0.54
    ürlich
    -0.50
     ""],
    -0.50
     Picchu
    -0.48
    SPATH
    -0.48
    ANP
    -0.48
     mikrofon
    -0.47
     gasp
    -0.45
     DSL
    -0.45
    EDEFAULT
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.69
    IALE
    0.62
     виправивши
    0.58
    LookAnd
    0.54
    UnsafeEnabled
    0.52
    WebElementEntity
    0.52
     Paglinawan
    0.50
    yip
    0.49
    chik
    0.49
     COMPAN
    0.49
    Activations Density 0.023%

    No Known Activations