© 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. 43428
    Prev
    Next
    INDEX
    Explanations

    cra

    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
    cra
    -0.56
     Bu
    -0.53
     F
    -0.51
     bu
    -0.50
    y
    -0.50
     The
    -0.49
     as
    -0.48
    держание
    -0.47
    ship
    -0.47
     f
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.86
     myſelf
    0.77
     ་་
    0.75
     Cæsar
    0.73
     houſe
    0.73
     hentai
    0.72
     purpoſe
    0.72
    InjectAttribute
    0.71
     pleaſure
    0.71
     متعلقه
    0.70
    Activations Density 0.073%

    No Known Activations