© 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. 97972
    Prev
    Next
    INDEX
    Explanations

    family

    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
    /');
    -0.74
     ‚
    -0.67
    ,‎
    -0.65
    />";
    -0.63
     onCancelled
    -0.63
    "';
    -0.63
     Мексичка
    -0.62
    ՚
    -0.61
     DbSet
    -0.61
    "])
    -0.60
    POSITIVE LOGITS
    GEBURTSDATUM
    0.57
    hopefully
    0.53
     faces
    0.50
     may
    0.49
     hopefully
    0.49
     is
    0.47
     was
    0.46
    IsContent
    0.45
    principalTable
    0.45
    Possibly
    0.43
    Activations Density 0.000%

    No Known Activations