© 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. 72340
    Prev
    Next
    INDEX
    Explanations

    large

    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
    يكب
    -0.91
     defaultstate
    -0.86
     Administrativna
    -0.81
    +#+#
    -0.79
     мәкалә
    -0.77
    variety
    -0.76
    antaranya
    -0.75
    tagHelperRunner
    -0.75
    WriteBarrier
    -0.75
    ranges
    -0.74
    POSITIVE LOGITS
     larger
    0.54
     bit
    0.52
     bigger
    0.50
     large
    0.47
     big
    0.46
     good
    0.45
     sm
    0.44
     little
    0.42
     w
    0.41
     few
    0.41
    Activations Density 0.001%

    No Known Activations