© 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. 0-CLT-HP
    7. 42661
    Prev
    Next
    INDEX
    Explanations

    correctness

    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
     open
    -1.27
    open
    -0.87
     correct
    -0.87
     terbuka
    -0.87
    Open
    -0.85
     abiertos
    -0.75
     Open
    -0.72
     ouvert
    -0.72
     openness
    -0.71
     deschis
    -0.71
    POSITIVE LOGITS
    VersionUID
    0.90
    AnchorStyles
    0.88
    tvguidetime
    0.81
     kasarigan
    0.80
    SharedCtor
    0.76
     мәкал
    0.75
    tagHelperRunner
    0.73
     nakalista
    0.70
    脚注の使い方
    0.69
    ArgsConstructor
    0.68
    Activations Density 0.037%

    No Known Activations