© 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. 20-CLT-HP
    7. 71667
    Prev
    Next
    INDEX
    Explanations

    call

    np_max-act-logits · 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
     Messages
    -0.95
     nahilalakip
    -0.86
     Motions
    -0.85
     messages
    -0.83
    messages
    -0.82
    Messages
    -0.82
    signals
    -0.82
     Signals
    -0.80
     signals
    -0.78
    MESSAGES
    -0.76
    POSITIVE LOGITS
     call
    0.61
     note
    0.59
     Counties
    0.52
     order
    0.46
     sigh
    0.45
     command
    0.44
    dies
    0.44
    dians
    0.44
     counties
    0.43
     distress
    0.43
    Activations Density 0.000%

    No Known Activations