© 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. 95746
    Prev
    Next
    INDEX
    Explanations

    multiplication and counting

    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
     loaded
    -1.15
     counting
    -1.12
     multiplying
    -1.11
     multiplied
    -1.05
     multiply
    -1.03
    loaded
    -1.01
     Multiply
    -0.98
     Counting
    -0.86
    Loaded
    -0.84
     Loaded
    -0.84
    POSITIVE LOGITS
    DebuggerNonUser
    0.73
    +#+#
    0.73
     HasFactory
    0.68
    ValueGenerated
    0.66
    WireFormatLite
    0.65
    (!__
    0.63
    principalTable
    0.61
    :✨
    0.60
    WithIOException
    0.59
    setVerticalGroup
    0.58
    Activations Density 0.242%

    No Known Activations