© 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. 1-CLT-HP
    7. 8628
    Prev
    Next
    INDEX
    Explanations

    "sh"

    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
    EndContext
    -0.64
     Sh
    -0.59
    ]--;
    -0.57
     ویکی‌پدی
    -0.55
    timedelta
    -0.53
    الإنجليزية
    -0.52
    ksikon
    -0.52
     migrator
    -0.52
    chum
    -0.51
     beginnetje
    -0.51
    POSITIVE LOGITS
    HtmlAttribute
    0.54
    ="@+
    0.49
    mbitos
    0.48
     Neuen
    0.41
    })).
    0.41
     segni
    0.41
     _("
    0.40
    følgelig
    0.39
     confronti
    0.39
    ρων
    0.38
    Activations Density 0.016%

    No Known Activations