© 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. 5-CLT-HP
    7. 91743
    Prev
    Next
    INDEX
    Explanations

    Companies and websites

    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
     reappeared
    -0.55
     curfew
    -0.53
     swims
    -0.52
     abducted
    -0.52
     pseudos
    -0.51
     republished
    -0.50
     bridegroom
    -0.49
     dusted
    -0.49
    Démographie
    -0.49
    SupportActionBar
    -0.49
    POSITIVE LOGITS
    ®.
    0.63
    ®
    0.57
    ®,
    0.57
    はじめに
    0.53
    <sup>
    0.52
     ®
    0.51
    ™.
    0.49
    ©
    0.49
     or
    0.48
     ${
    0.48
    Activations Density 0.003%

    No Known Activations