© 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. 94521
    Prev
    Next
    INDEX
    Explanations

    imbib

    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
     Efq
    -0.97
     myſelf
    -0.91
     Jefus
    -0.88
     Majefty
    -0.86
     Shakspeare
    -0.84
     poffe
    -0.80
     Galile
    -0.80
     ſever
    -0.78
     fevere
    -0.77
     houſe
    -0.77
    POSITIVE LOGITS
    ly
    0.79
    mente
    0.63
     χ
    0.60
    LY
    0.57
     دیکھیے
    0.54
     hi
    0.50
    ever
    0.48
    OURS
    0.48
     bParam
    0.48
    dingen
    0.47
    Activations Density 0.096%

    No Known Activations