© 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. 5957
    Prev
    Next
    INDEX
    Explanations

    and,

    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
    ubon
    -0.59
    telsen
    -0.45
    CEED
    -0.45
     understanding
    -0.44
    MergeFrom
    -0.44
     swallow
    -0.43
    tolist
    -0.43
    bori
    -0.43
     understand
    -0.43
    achu
    -0.43
    POSITIVE LOGITS
     المعيارى
    0.75
    تقاوى
    0.70
    expandindo
    0.66
     ragazze
    0.61
    enumii
    0.61
     paziente
    0.59
     població
    0.59
    IntoConstraints
    0.58
    RenderAtEndOf
    0.57
    enumi
    0.56
    Activations Density 0.004%

    No Known Activations