© 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. 77267
    Prev
    Next
    INDEX
    Explanations

    Technical Documents

    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
    bootstrapcdn
    -0.68
     समीक्षक
    -0.67
    EndTag
    -0.63
    MessageOf
    -0.60
    LookAnd
    -0.59
     geldig
    -0.57
    yntaxException
    -0.57
     ErrIntOverflow
    -0.57
    </thead>
    -0.56
    htë
    -0.54
    POSITIVE LOGITS
    LayoutConstraint
    0.46
    yelitis
    0.45
     bu
    0.45
    脚注の使い方
    0.42
     backs
    0.41
    Тема
    0.41
    Accessors
    0.41
     speeds
    0.41
     zvuky
    0.40
    ielsen
    0.40
    Activations Density 0.000%

    No Known Activations