© 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. 40719
    Prev
    Next
    INDEX
    Explanations

    variants

    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
     variant
    -0.74
     Variants
    -0.71
    variant
    -0.67
     perspectiva
    -0.66
     variants
    -0.65
     perspective
    -0.64
    perspective
    -0.63
     cherchés
    -0.60
    virons
    -0.60
     Variant
    -0.59
    POSITIVE LOGITS
     popolare
    0.57
     aigu
    0.54
    (||
    0.54
    xor
    0.52
    IsContent
    0.52
    InvalidProtocol
    0.51
     geodes
    0.51
     plot
    0.50
     Nunn
    0.50
    principalTable
    0.50
    Activations Density 0.321%

    No Known Activations