© 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. 8967
    Prev
    Next
    INDEX
    Explanations

    evaluation or judgement

    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
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.97
     pleaſure
    -0.96
     ―――――
    -0.95
     itſelf
    -0.93
     myſelf
    -0.93
     ſche
    -0.93
    GEBURTSDATUM
    -0.92
     Jefus
    -0.91
     cauſe
    -0.89
     EconPapers
    -0.89
    POSITIVE LOGITS
    .
    0.95
     
    0.93
     to
    0.75
    ↵
    0.75
    '
    0.73
    ’
    0.69
    <bos>
    0.68
    ↵↵
    0.66
    :
    0.65
    The
    0.65
    Activations Density 0.659%

    No Known Activations