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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44033
    Prev
    Next
    INDEX
    Explanations

    potential negativity

    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
    featureID
    -0.90
     financeira
    -0.82
    MessageTagHelper
    -0.78
     câte
    -0.78
     GeoNames
    -0.77
     colectiva
    -0.77
     propOrder
    -0.77
    Демографія
    -0.76
     itſelf
    -0.75
     Efq
    -0.74
    POSITIVE LOGITS
    ,
    0.49
    enumi
    0.49
     Sha
    0.48
     M
    0.48
     of
    0.47
    ppus
    0.47
     for
    0.47
    mainAxisSize
    0.46
     di
    0.45
     cas
    0.45
    Activations Density 0.070%

    No Known Activations