© 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. 95447
    Prev
    Next
    INDEX
    Explanations

    Disclaimer

    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
    はじめに
    -0.65
    Jeografia
    -0.60
    AVES
    -0.59
    alamus
    -0.55
    rxjs
    -0.53
    alas
    -0.52
    LAZY
    -0.52
     Shepard
    -0.51
     (?,
    -0.51
    stdbool
    -0.51
    POSITIVE LOGITS
    ed
    0.73
    ly
    0.67
    hood
    0.63
    Zeneca
    0.63
     BoxFit
    0.59
    ſelf
    0.55
     Roskov
    0.55
    ReusableCell
    0.54
    ized
    0.53
     panoramique
    0.53
    Activations Density 0.076%

    No Known Activations