© 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. 91807
    Prev
    Next
    INDEX
    Explanations

    the

    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
     flexibles
    -0.46
    Демографія
    -0.46
    fertig
    -0.40
     Camin
    -0.40
    rungsseite
    -0.39
     Ribera
    -0.38
    MigrationBuilder
    -0.38
    verwijspagina
    -0.37
     Química
    -0.36
     Wirksamkeit
    -0.36
    POSITIVE LOGITS
     Question
    0.73
     Important
    0.67
    $.}
    0.65
     getItemId
    0.64
     Main
    0.63
     kasarigan
    0.62
    Datuak
    0.62
     Corresponding
    0.62
    __':
    0.60
    ruptedException
    0.60
    Activations Density 0.001%

    No Known Activations