© 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. 73127
    Prev
    Next
    INDEX
    Explanations

    tika

    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
    UnknownFields
    -0.75
     كومونز
    -0.71
    ViewImports
    -0.63
    cartão
    -0.59
     defStyle
    -0.59
    httphttps
    -0.59
    ύπ
    -0.58
    IntoConstraints
    -0.56
     nostrils
    -0.56
    ometrial
    -0.55
    POSITIVE LOGITS
    gesch
    0.58
    +#+#
    0.46
    gel
    0.43
     im
    0.42
    false
    0.40
     확인함
    0.40
     ό
    0.39
    band
    0.39
     Moro
    0.39
     false
    0.39
    Activations Density 0.007%

    No Known Activations