© 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. 77961
    Prev
    Next
    INDEX
    Explanations

    -er words

    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
    OGND
    -0.77
    Autoritní
    -0.71
     Roskov
    -0.69
    EndProject
    -0.66
    expandindo
    -0.66
     kasarigan
    -0.63
    IsContent
    -0.60
    WebElementEntity
    -0.59
    MENAFN
    -0.59
    WithEmail
    -0.58
    POSITIVE LOGITS
     of
    0.56
    .
    0.55
    ,
    0.54
     bebas
    0.53
    rawDesc
    0.51
     uğ
    0.49
    aber
    0.47
    oja
    0.47
    extra
    0.47
    extractor
    0.46
    Activations Density 0.018%

    No Known Activations