© 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. 42345
    Prev
    Next
    INDEX
    Explanations

    degree

    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
     againſt
    -0.75
    \{\\
    -0.70
     houſe
    -0.69
     whoſe
    -0.68
     faſt
    -0.68
     ſever
    -0.67
     ſtate
    -0.66
     Diſ
    -0.66
     Houſe
    -0.64
     Anſ
    -0.64
    POSITIVE LOGITS
     get
    0.83
     be
    0.77
     have
    0.77
     find
    0.69
     assume
    0.66
     see
    0.64
    Välislingid
    0.63
     consider
    0.63
     create
    0.63
     recognize
    0.62
    Activations Density 0.127%

    No Known Activations