© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93290
    Prev
    Next
    INDEX
    Explanations

    code

    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
    StreamWriter
    -0.55
    cobra
    -0.50
     />);
    -0.50
    CardBody
    -0.47
    <>());
    -0.46
    [];
    -0.44
    بر
    -0.44
    ruptedException
    -0.43
    inheit
    -0.42
    IMPORTED
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    0.75
    rawtypes
    0.66
    XmlEnum
    0.63
     estekak
    0.61
    WebVitals
    0.58
     esternos
    0.58
    ValueStyle
    0.56
     Réponses
    0.55
    ContentAlignment
    0.54
    SourceChecksum
    0.53
    Activations Density 0.004%

    No Known Activations