© 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. 16049
    Prev
    Next
    INDEX
    Explanations

    places

    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
    .
    -0.65
    '
    -0.64
     
    -0.59
    :
    -0.56
    <bos>
    -0.56
    ’
    -0.55
    ,
    -0.54
    \
    -0.54
    ↵
    -0.53
     ro
    -0.53
    POSITIVE LOGITS
     Majefty
    1.26
     purpoſe
    1.23
     myſelf
    1.21
     Monfieur
    1.17
     greateſt
    1.16
     houſe
    1.15
     ſtate
    1.15
     Anſ
    1.14
     pleaſure
    1.14
    Jeografia
    1.12
    Activations Density 0.010%

    No Known Activations