© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77132
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · 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
     MainAxisSize
    -0.72
    SBATCH
    -0.69
     defStyle
    -0.68
    endpush
    -0.66
    发表于
    -0.66
    ForRow
    -0.64
    WithIOException
    -0.64
    AxisAlignment
    -0.63
     pleaſure
    -0.62
    
    -0.62
    POSITIVE LOGITS
     Es
    0.41
    ژ
    0.40
    Kanpo
    0.39
     ES
    0.36
    ıll
    0.36
     Event
    0.35
    cale
    0.35
    vent
    0.35
    :✨
    0.35
    Es
    0.34
    Activations Density 0.000%

    No Known Activations