© 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. 1-CLT-HP
    7. 15080
    Prev
    Next
    INDEX
    Explanations

    a

    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
     ever
    -0.97
    Chham
    -0.84
    BeginContext
    -0.76
    IsMutable
    -0.76
     فريبيس
    -0.75
    MENAFN
    -0.75
    Viitteet
    -0.73
     Chwiliwch
    -0.71
     EVER
    -0.71
    رشف
    -0.68
    POSITIVE LOGITS
    hat
    0.42
    away
    0.41
    もしれない
    0.39
     similar
    0.38
    other
    0.38
    ніципалі
    0.38
    when
    0.37
     priori
    0.37
    hem
    0.37
    similar
    0.36
    Activations Density 0.008%

    No Known Activations