© 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. 16142
    Prev
    Next
    INDEX
    Explanations

    giving advice

    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
    <bos>
    -0.85
     in
    -0.69
     to
    -0.52
    ,
    -0.51
     and
    -0.50
     løpet
    -0.50
    feel
    -0.50
     armées
    -0.50
     on
    -0.49
     semula
    -0.49
    POSITIVE LOGITS
     Houſe
    0.70
     Efq
    0.70
    +#+#
    0.66
     getItemId
    0.66
     houſe
    0.65
     Monfieur
    0.63
     Jefus
    0.61
    
    0.61
     Theſe
    0.61
     Perſ
    0.60
    Activations Density 0.570%

    No Known Activations