© 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. 5-CLT-HP
    7. 96021
    Prev
    Next
    INDEX
    Explanations

    text formatting

    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
     &___
    -0.49
    esModule
    -0.47
    insics
    -0.47
     resourceCulture
    -0.45
     INTERESAR
    -0.44
     Mapa
    -0.43
     indisponible
    -0.43
    UnifiedTopology
    -0.43
     estekak
    -0.42
    '">
    -0.42
    POSITIVE LOGITS
    numbers
    0.67
    Бахар
    0.66
    scriptcase
    0.66
    spaced
    0.65
     spaces
    0.65
    space
    0.63
     space
    0.61
    paces
    0.61
     numberOfRows
    0.60
     numbers
    0.60
    Activations Density 0.003%

    No Known Activations