© 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. 94373
    Prev
    Next
    INDEX
    Explanations

    problems

    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
     normaux
    -1.12
     supérieurs
    -1.02
     colorés
    -0.98
     fermés
    -0.97
     dépens
    -0.96
     quelcon
    -0.95
     traditionnels
    -0.94
     nationaux
    -0.94
     scolaires
    -0.94
     militaires
    -0.93
    POSITIVE LOGITS
    ised
    0.63
     ed
    0.54
    ness
    0.54
    idential
    0.53
     “
    0.52
     full
    0.51
     air
    0.51
     privacy
    0.51
     Enix
    0.51
    indd
    0.50
    Activations Density 0.326%

    No Known Activations