© 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. 77053
    Prev
    Next
    INDEX
    Explanations

    the

    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
    AndEndTag
    -0.85
    MergeFrom
    -0.70
     متعلقه
    -0.69
    mergeFrom
    -0.62
    MetaType
    -0.61
     EconPapers
    -0.59
    StoryboardSegue
    -0.56
    Parcelize
    -0.56
     proposées
    -0.56
    CPtr
    -0.56
    POSITIVE LOGITS
    BagConstraints
    0.59
    談社
    0.50
     art
    0.49
    ICALS
    0.49
     blood
    0.49
    //
    0.43
     arts
    0.40
    art
    0.40
    garn
    0.40
    ็น
    0.39
    Activations Density 0.003%

    No Known Activations