© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 912
    Prev
    Next
    INDEX
    Explanations

    Starts with "tre"

    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
     AssemblyCulture
    -0.71
     GenerationType
    -0.67
    apunov
    -0.62
    httphttps
    -0.61
    UIControlState
    -0.61
    itrile
    -0.61
     Confusion
    -0.60
    +:+
    -0.60
     crucible
    -0.59
    disambiguation
    -0.58
    POSITIVE LOGITS
    asure
    0.45
    nor
    0.41
    ury
    0.41
     Trit
    0.41
    sed
    0.40
    pass
    0.39
    ymce
    0.38
    Tre
    0.38
    mend
    0.37
    Small
    0.36
    Activations Density 0.023%

    No Known Activations