© 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. 8653
    Prev
    Next
    INDEX
    Explanations

    exception

    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
     error
    -0.96
     Error
    -0.92
    RectangleBorder
    -0.88
    error
    -0.88
    Error
    -0.84
    ERROR
    -0.77
     ERROR
    -0.75
    Errors
    -0.74
     errores
    -0.71
     Errors
    -0.69
    POSITIVE LOGITS
    órum
    0.56
     conditions
    0.53
    conditions
    0.51
     dataSnapshot
    0.48
     messages
    0.47
    Raised
    0.46
     Conditions
    0.45
     raised
    0.44
    raised
    0.44
    Conditions
    0.43
    Activations Density 0.072%

    No Known Activations