© 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. 0-CLT-HP
    7. 95788
    Prev
    Next
    INDEX
    Explanations

    authentication, calibration, graduation

    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
     שוליים
    -0.83
     يتيمه
    -0.74
     basalt
    -0.72
     authenticated
    -0.71
     OMITBAD
    -0.71
     calibrated
    -0.69
    
    -0.69
     calibration
    -0.68
     quartzite
    -0.68
    ThroughAttribute
    -0.66
    POSITIVE LOGITS
    isler
    0.54
     in
    0.52
    ]}>
    0.50
     his
    0.50
    isted
    0.48
     her
    0.47
    iset
    0.47
    ))->
    0.47
     cur
    0.47
    ערכת
    0.46
    Activations Density 0.126%

    No Known Activations