© 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. 42359
    Prev
    Next
    INDEX
    Explanations

    Bic

    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
     getItemCount
    -0.88
     myſelf
    -0.85
     دیکھیے
    -0.85
     Bic
    -0.81
     useParams
    -0.80
    awtextra
    -0.79
    ]='\
    -0.79
     bic
    -0.78
    GEBURTSDATUM
    -0.77
     useStyles
    -0.76
    POSITIVE LOGITS
    s
    0.69
    r
    0.58
    ery
    0.55
    ness
    0.51
    is
    0.51
    t
    0.51
    sad
    0.50
    or
    0.49
    us
    0.49
    re
    0.49
    Activations Density 0.855%

    No Known Activations