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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90689
    Prev
    Next
    INDEX
    Explanations

    cost

    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
     cost
    -1.17
    cost
    -0.97
     Cost
    -0.90
    Cost
    -0.87
     COST
    -0.73
    COST
    -0.71
     costs
    -0.65
     costi
    -0.63
    costs
    -0.62
     costo
    -0.61
    POSITIVE LOGITS
     prophylaxis
    0.63
     vorticity
    0.62
     autorytatywna
    0.60
     transduction
    0.59
     Bioaccumulative
    0.57
     estoppel
    0.57
    ferential
    0.57
     transfusion
    0.56
    ніципалі
    0.56
     appropriation
    0.54
    Activations Density 0.225%

    No Known Activations