© 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. 72322
    Prev
    Next
    INDEX
    Explanations

    code words

    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
    DataAnnotations
    -0.59
    requireNonNull
    -0.52
    上角
    -0.49
     nevera
    -0.49
     חיצוניים
    -0.48
    ,:);
    -0.47
     (!__
    -0.47
    IsNull
    -0.47
     Norm
    -0.46
     Aver
    -0.46
    POSITIVE LOGITS
     ErrIntOverflow
    0.62
    Hochspringen
    0.58
    ocumented
    0.56
    WithIOException
    0.53
    oredCriteria
    0.51
    PerformLayout
    0.50
    -------
    0.50
    sidemargin
    0.49
    PubMed
    0.49
    IonicModule
    0.48
    Activations Density 0.000%

    No Known Activations