© 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. 0-CLT-HP
    7. 43092
    Prev
    Next
    INDEX
    Explanations

    rules

    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
     rules
    -1.36
    rules
    -1.36
    Rules
    -1.26
     Rules
    -1.23
     RULES
    -1.20
     règles
    -1.19
     regole
    -1.09
    RULES
    -1.09
     regler
    -1.06
     regras
    -1.02
    POSITIVE LOGITS
     for
    0.59
    ets
    0.53
     that
    0.51
    ек
    0.50
     almo
    0.50
    nk
    0.48
    lr
    0.45
    hower
    0.44
    et
    0.43
     cellspacing
    0.42
    Activations Density 0.047%

    No Known Activations