© 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. 91076
    Prev
    Next
    INDEX
    Explanations

    development

    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
     gynhyrchwyd
    -0.75
     Ressource
    -0.69
     AppCompatTheme
    -0.66
    ForRow
    -0.64
    '],
    -0.63
     дописавши
    -0.62
    ThroughAttribute
    -0.62
     propOrder
    -0.62
    ']->
    -0.60
    CastException
    -0.60
    POSITIVE LOGITS
    <bos>
    0.73
     styles
    0.67
    styles
    0.59
    Styles
    0.56
     where
    0.53
    where
    0.50
     Styles
    0.49
    RenderAtEndOf
    0.46
     STYLES
    0.45
     that
    0.45
    Activations Density 0.001%

    No Known Activations