© 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. 95759
    Prev
    Next
    INDEX
    Explanations

    fraction

    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
     ratio
    -1.03
     fraction
    -1.01
    sen
    -0.98
    Fraction
    -0.91
     Ratio
    -0.90
    ratio
    -0.89
     Fraction
    -0.85
     ratios
    -0.85
    proportion
    -0.84
     Ratios
    -0.83
    POSITIVE LOGITS
    SequentialGroup
    0.77
    ValueStyle
    0.74
    ality
    0.71
     bezeichneter
    0.67
     IBOutlet
    0.66
     متعلقه
    0.64
    ally
    0.63
    arity
    0.62
    ative
    0.61
     layui
    0.61
    Activations Density 0.079%

    No Known Activations