© 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. 95366
    Prev
    Next
    INDEX
    Explanations

    vari

    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
     grade
    -0.71
     friendly
    -0.68
    arus
    -0.62
    aver
    -0.60
     present
    -0.55
    rain
    -0.53
     Grade
    -0.53
     “
    -0.50
     afe
    -0.50
    vari
    -0.50
    POSITIVE LOGITS
     itſelf
    1.04
     pleaſure
    1.04
     myſelf
    1.02
     Monfieur
    0.99
     Efq
    0.96
     poffible
    0.94
     poffe
    0.94
     ſeveral
    0.93
     Jefus
    0.93
     greateſt
    0.93
    Activations Density 0.057%

    No Known Activations