© 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. 0-CLT-HP
    7. 94362
    Prev
    Next
    INDEX
    Explanations

    accounting

    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
     wood
    -1.52
    Wood
    -1.09
     Wood
    -1.07
     WOOD
    -0.98
     legno
    -0.97
     accounting
    -0.94
    wood
    -0.92
     Accounting
    -0.91
    WOOD
    -0.90
     Anſ
    -0.84
    POSITIVE LOGITS
     الحره
    0.69
    newBuilder
    0.57
     كومونز
    0.57
    Personendaten
    0.56
     the
    0.53
    localctx
    0.53
     bau
    0.53
     estimés
    0.52
     bes
    0.52
    sch
    0.52
    Activations Density 0.041%

    No Known Activations