© 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. 1-CLT-HP
    7. 15975
    Prev
    Next
    INDEX
    Explanations

    who

    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
     are
    -0.80
     were
    -0.78
     have
    -0.72
    bootstrapcdn
    -0.66
    <bos>
    -0.64
     took
    -0.63
     had
    -0.60
    WriteBarrier
    -0.58
     attended
    -0.57
     did
    -0.55
    POSITIVE LOGITS
    tling
    0.67
    domada
    0.57
    breeding
    0.56
    holding
    0.55
     rearing
    0.55
    länd
    0.55
     jeito
    0.55
     chattering
    0.55
    xious
    0.54
    -/
    0.53
    Activations Density 0.009%

    No Known Activations