© 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. 20-CLT-HP
    7. 77919
    Prev
    Next
    INDEX
    Explanations

    technical or scientific text

    np_max-act-logits · 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
     fej
    -0.45
     zależ
    -0.44
    ارض
    -0.44
     promosi
    -0.44
     electricidad
    -0.44
    áctico
    -0.43
    rounds
    -0.42
     blå
    -0.42
    finding
    -0.42
     attendu
    -0.42
    POSITIVE LOGITS
    mybatisplus
    0.86
     <<<<<<<<<<<<<<
    0.69
     @"/
    0.65
    StoryboardSegue
    0.61
    stdc
    0.59
    windowFixed
    0.59
    HALT
    0.58
     ErrIntOverflow
    0.58
    Aholisi
    0.57
    AnchorStyles
    0.56
    Activations Density 0.002%

    No Known Activations