© 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. 16172
    Prev
    Next
    INDEX
    Explanations

    Hexadecimal codes

    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
    i
    -0.57
    P
    -0.53
    C
    -0.52
    a
    -0.50
    <bos>
    -0.49
    y
    -0.49
    ti
    -0.49
     her
    -0.47
    iti
    -0.46
    R
    -0.46
    POSITIVE LOGITS
     Theſe
    0.82
    তথ্যসূত্র
    0.77
     Monfieur
    0.75
     becauſe
    0.73
     nakalista
    0.73
     myſelf
    0.73
     themſelves
    0.72
     Administrativna
    0.70
     ſmall
    0.70
    WithIOException
    0.70
    Activations Density 0.125%

    No Known Activations