© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 94978
    Prev
    Next
    INDEX
    Explanations

    believer

    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
     Cæsar
    -1.17
    izations
    -1.01
     Monfieur
    -1.01
     Majefty
    -0.99
     Shakspeare
    -0.97
     ainfi
    -0.96
     theſe
    -0.94
     Theſe
    -0.92
     Houſe
    -0.91
     ſeveral
    -0.91
    POSITIVE LOGITS
     in
    0.60
     a
    0.56
     "
    0.56
     “
    0.55
     particular
    0.52
     as
    0.50
     or
    0.50
     Cor
    0.50
     an
    0.49
     complete
    0.49
    Activations Density 1.167%

    No Known Activations