© 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. 90928
    Prev
    Next
    INDEX
    Explanations

    gardens and/or genitalia

    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
     Garden
    -0.97
    Garden
    -0.92
    garden
    -0.89
     GARDEN
    -0.89
     garden
    -0.84
     définiti
    -0.75
    arangay
    -0.68
     pitié
    -0.68
     giardino
    -0.67
    tonsoft
    -0.66
    POSITIVE LOGITS
    i
    0.69
    ias
    0.60
    ia
    0.53
    is
    0.52
    ies
    0.52
    ier
    0.51
    ic
    0.51
    iers
    0.50
    ie
    0.50
    cloudflare
    0.49
    Activations Density 0.072%

    No Known Activations