© 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. 77324
    Prev
    Next
    INDEX
    Explanations

    Technical/legal contextual information

    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
     betweenstory
    -0.93
    Topics
    -0.93
    chute
    -0.89
     Topics
    -0.88
     Themes
    -0.85
    Themes
    -0.82
    省市镇
    -0.82
     SUBJECTS
    -0.81
     Subjects
    -0.78
     TOPICS
    -0.78
    POSITIVE LOGITS
     question
    0.35
    .,
    0.33
    >,
    0.33
    »
    0.32
    /
    0.30
     name
    0.29
    .
    0.29
     highly
    0.29
    さんも
    0.28
    $,
    0.28
    Activations Density 0.005%

    No Known Activations