© 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. 90845
    Prev
    Next
    INDEX
    Explanations

    of

    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
     يتيمه
    -0.83
     ModelExpression
    -0.79
    
    -0.75
     MaterialApp
    -0.74
    PhysRevD
    -0.72
     GlobalKey
    -0.69
     ProtoMessage
    -0.68
    TestBed
    -0.68
    writeFieldEnd
    -0.68
    OGND
    -0.66
    POSITIVE LOGITS
     at
    0.63
     not
    0.56
     all
    0.47
     democracy
    0.47
     continúas
    0.43
     nationalism
    0.43
     humanity
    0.42
     womanhood
    0.42
    __*/
    0.42
     masculinity
    0.41
    Activations Density 0.001%

    No Known Activations