© 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. 72027
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     Normdatei
    -0.66
     للمعارف
    -0.63
    RenderAtEndOf
    -0.59
    dane
    -0.52
    Carriera
    -0.51
    rrggbb
    -0.50
    LAH
    -0.49
     connexes
    -0.49
    ミナル
    -0.49
     prestations
    -0.48
    POSITIVE LOGITS
    NameInMap
    0.57
    dafx
    0.56
    DebuggerNonUser
    0.50
    EXTERN
    0.47
     Comprometido
    0.45
    WillAppear
    0.45
    yntaxException
    0.45
    qus
    0.44
     تعدى
    0.44
     parang
    0.43
    Activations Density 0.005%

    No Known Activations