© 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. 43673
    Prev
    Next
    INDEX
    Explanations

    )

    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
    principalColumn
    -0.99
    AccessorTable
    -0.79
     виправивши
    -0.77
     AssemblyCulture
    -0.73
     &___
    -0.73
    InjectAttribute
    -0.71
    __(/*!
    -0.67
    nteral
    -0.66
     interacted
    -0.65
    holding
    -0.64
    POSITIVE LOGITS
     pygame
    0.50
     resemblance
    0.47
    Thankyou
    0.45
     γρα
    0.45
    ness
    0.44
     BMC
    0.44
     STATES
    0.42
     Crusade
    0.42
     nobili
    0.42
     resemb
    0.41
    Activations Density 0.015%

    No Known Activations