© 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. 43119
    Prev
    Next
    INDEX
    Explanations

    cooking or art

    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
     itſelf
    -0.89
     pleaſure
    -0.87
    ſelf
    -0.86
     photolibrary
    -0.84
     الرياضيه
    -0.83
     Efq
    -0.83
     greateſt
    -0.83
     Monfieur
    -0.82
     ſmall
    -0.82
     himſelf
    -0.81
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
    (!__
    0.46
    .
    0.46
    DebuggerNonUser
    0.43
     ویکی‌پدیا
    0.43
     an
    0.43
    sto
    0.43
    stm
    0.42
     and
    0.40
     to
    0.40
    Activations Density 0.100%

    No Known Activations