© 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. 1-CLT-HP
    7. 341
    Prev
    Next
    INDEX
    Explanations

    Folio

    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
     folio
    -1.35
     Folio
    -1.33
    Folio
    -0.82
    folio
    -0.75
     foli
    -0.55
     oreille
    -0.54
    loroethane
    -0.53
     actuelles
    -0.51
     feux
    -0.47
     rispar
    -0.47
    POSITIVE LOGITS
     Society
    0.72
    Society
    0.68
    StructEnd
    0.61
     society
    0.60
     SOCIETY
    0.58
     viewType
    0.57
     تضيفلها
    0.53
    ///</
    0.51
    principalTable
    0.51
     Soc
    0.50
    Activations Density 0.001%

    No Known Activations