© 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. 0-CLT-HP
    7. 94749
    Prev
    Next
    INDEX
    Explanations

    Unrelated 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
    ThroughAttribute
    -0.57
     يتيمه
    -0.57
    MigrationBuilder
    -0.55
     to
    -0.54
    logging
    -0.52
    ụng
    -0.51
    hnung
    -0.51
    ädie
    -0.51
    enterOuterAlt
    -0.49
    estone
    -0.49
    POSITIVE LOGITS
    ########.
    0.81
    OGND
    0.61
    出版年
    0.61
    +#+
    0.60
     Sélectionnez
    0.54
    ագրություններ
    0.54
    abestanden
    0.52
     الدولى
    0.52
     tanong
    0.52
     readFile
    0.52
    Activations Density 1.837%

    No Known Activations