© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91004
    Prev
    Next
    INDEX
    Explanations

    Incoherent text

    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
    Negative Logits
     Czechoslovakia
    -0.44
     afrontar
    -0.44
    tamment
    -0.42
     Conselho
    -0.42
     totiž
    -0.38
    Compat
    -0.38
    ""
    -0.38
    ัว
    -0.38
    Drawable
    -0.37
     Consejo
    -0.37
    POSITIVE LOGITS
    Datuak
    0.85
    //
    0.85
    MLLoader
    0.84
     الرياضيه
    0.76
    RemoveField
    0.71
     CURRENT
    0.65
    kuuta
    0.65
     CLOSED
    0.62
    URLException
    0.61
     فريبيس
    0.60
    Activations Density 0.000%

    No Known Activations