© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92882
    Prev
    Next
    INDEX
    Explanations

    erectile

    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
     समीक्षक
    -0.79
    larger
    -0.63
     conservé
    -0.63
     larger
    -0.58
     án
    -0.57
     cai
    -0.56
    record
    -0.55
    ();)
    -0.54
    noti
    -0.54
     apporté
    -0.54
    POSITIVE LOGITS
     dysfunction
    0.58
     Dysfunction
    0.56
     ब्रेकडाउन
    0.52
    DebuggerNonUser
    0.52
    Hentet
    0.49
     broken
    0.49
     تضيفلها
    0.49
    URLException
    0.48
    astéroïdes
    0.46
     Fehl
    0.45
    Activations Density 0.003%

    No Known Activations