© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97501
    Prev
    Next
    INDEX
    Explanations

    pronounced

    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
     خارجية
    -0.46
    IVEREF
    -0.43
     a
    -0.41
    ReusableCell
    -0.41
     Riproduzione
    -0.40
     gyer
    -0.40
    gypte
    -0.40
    tainen
    -0.38
    VarChar
    -0.38
     such
    -0.38
    POSITIVE LOGITS
    SequentialGroup
    0.93
    awtextra
    0.73
    VersionUID
    0.72
    devamını
    0.69
     thiệu
    0.68
    期刊论文
    0.66
    pédie
    0.66
    참고
    0.66
     noqa
    0.66
     Newsroom
    0.65
    Activations Density 0.003%

    No Known Activations