© 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. 0-CLT-HP
    7. 43732
    Prev
    Next
    INDEX
    Explanations

    like

    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
     like
    -1.14
    like
    -0.93
    Like
    -0.87
    '
    -0.80
     Like
    -0.73
    ’
    -0.71
    ‘
    -0.69
     вроде
    -0.63
    M
    -0.61
    Your
    -0.60
    POSITIVE LOGITS
    
    0.95
     BoxFit
    0.94
    SequentialGroup
    0.88
    GEBURTSDATUM
    0.84
    ]--;
    0.83
    extAlignment
    0.82
    HasAnnotation
    0.82
     }}$}
    0.81
    ]")]
    0.77
     AdapterView
    0.77
    Activations Density 0.739%

    No Known Activations