© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 93102
    Prev
    Next
    INDEX
    Explanations

    beaten

    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
    burned
    -0.73
    cerin
    -0.70
    ichio
    -0.68
     ostavi
    -0.68
    الحياه
    -0.68
    Gemeinden
    -0.66
    uggling
    -0.66
     burned
    -0.65
     cursed
    -0.63
    Xaml
    -0.62
    POSITIVE LOGITS
    ?");
    0.68
    ."));
    0.68
    neſs
    0.63
    ?')
    0.60
    ."),
    0.59
    ?")
    0.58
    .")]
    0.58
    */)
    0.57
     itſelf
    0.56
     ?",
    0.53
    Activations Density 0.347%

    No Known Activations