© 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. 0-CLT-HP
    7. 41955
    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
    expandindo
    -0.71
     مشين
    -0.61
     an
    -0.59
    .
    -0.59
     a
    -0.56
     kasarigan
    -0.53
    richTextPanel
    -0.53
     under
    -0.52
    :+:
    -0.51
     you
    -0.49
    POSITIVE LOGITS
     ſtate
    0.86
     itſelf
    0.81
     ་་
    0.78
     ―――――
    0.74
     faſt
    0.74
     uſe
    0.74
     ſind
    0.73
     Anſ
    0.73
     Reſ
    0.73
     ſtand
    0.72
    Activations Density 0.203%

    No Known Activations