© 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. 6025
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Geplaatst
    -0.91
    ArrowToggle
    -0.80
    Jeografia
    -0.79
    تقاوى
    -0.73
    afficheront
    -0.68
     démocr
    -0.64
    ьаж
    -0.63
     mélang
    -0.63
     réfrig
    -0.61
     Roskov
    -0.61
    POSITIVE LOGITS
     a
    0.59
     institute
    0.53
     dust
    0.51
     preparing
    0.51
    FormsModule
    0.50
    .
    0.50
     building
    0.50
     real
    0.49
     instrument
    0.49
     bay
    0.48
    Activations Density 0.002%

    No Known Activations