© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    interpretation/meaning

    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
    Negative Logits
     interpretation
    -1.47
     Interpretation
    -1.41
     INTERPRET
    -1.37
    interpretation
    -1.33
    Interpretation
    -1.33
     interpreting
    -1.23
    interprétation
    -1.23
     interpretations
    -1.21
     interpreted
    -1.16
     interpret
    -1.13
    POSITIVE LOGITS
     of
    0.59
    ropoda
    0.50
    allo
    0.48
    ,
    0.47
     Act
    0.43
    derd
    0.42
    s
    0.42
     @
    0.42
     required
    0.41
     pod
    0.41
    Activations Density 0.019%

    No Known Activations