© 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. 4-CLT-HP
    7. 739
    Prev
    Next
    INDEX
    Explanations

    Context variety

    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
    +#+#
    -0.80
    spaceBetween
    -0.49
    SizeF
    -0.47
    ftagPool
    -0.46
    abestanden
    -0.43
     свое
    -0.43
     swoich
    -0.42
     своих
    -0.42
    getDescriptor
    -0.42
    itosti
    -0.42
    POSITIVE LOGITS
    例句
    0.63
    مصادر
    0.61
     Cous
    0.60
     BoxDecoration
    0.56
     Audiodateien
    0.56
    kurat
    0.56
    données
    0.55
     sonst
    0.55
     samples
    0.55
     soups
    0.54
    Activations Density 0.018%

    No Known Activations