© 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. 4-CLT-HP
    7. 791
    Prev
    Next
    INDEX
    Explanations

    translation/configurations

    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
    MigrationBuilder
    -0.73
    ValueStyle
    -0.68
    +#+#
    -0.65
    WaitGroup
    -0.65
     onAnimation
    -0.65
    Autoritní
    -0.63
    idation
    -0.60
    verwijspagina
    -0.59
    الحياه
    -0.58
     Figures
    -0.57
    POSITIVE LOGITS
     réguli
    0.53
     énorm
    0.47
    utenant
    0.47
     végét
    0.45
     žiad
    0.43
     récentes
    0.43
     båda
    0.42
    .$,
    0.42
     måtte
    0.42
    :],
    0.41
    Activations Density 0.277%

    No Known Activations