© 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. 5-CLT-HP
    7. 92072
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ErrUnexpectedEOF
    -0.62
    DataPropertyName
    -0.59
    </caption>
    -0.59
     חיצוניים
    -0.57
     cherchés
    -0.57
    providedIn
    -0.56
    voyer
    -0.56
    expandindo
    -0.55
    prüche
    -0.54
     kaynağından
    -0.53
    POSITIVE LOGITS
    UnknownFieldSet
    0.49
    Autoritní
    0.47
     >=",
    0.47
    MessageInfo
    0.46
     StatelessWidget
    0.46
     ModelExpression
    0.45
     Brennan
    0.44
     invokingState
    0.43
    alsa
    0.43
    듭
    0.42
    Activations Density 0.002%

    No Known Activations