© 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. 0-CLT-HP
    7. 95577
    Prev
    Next
    INDEX
    Explanations

    code, legal documents, articles

    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
     урна
    -0.55
    LEncoder
    -0.52
     createSlice
    -0.52
    ClientRect
    -0.51
    VersionUID
    -0.50
    createCanvas
    -0.50
    riwal
    -0.50
    Tembelea
    -0.49
     întâ
    -0.48
     getRule
    -0.48
    POSITIVE LOGITS
     Wikimedijinoj
    0.58
    })$}
    0.57
    __':
    0.56
    })).
    0.55
     }?>
    0.54
     MainAxisSize
    0.53
    ingly
    0.53
     StatelessWidget
    0.53
    ')}}"
    0.53
    __[
    0.53
    Activations Density 1.790%

    No Known Activations