© 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. 1-CLT-HP
    7. 10265
    Prev
    Next
    INDEX
    Explanations

    paro

    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
    rungsseite
    -0.53
     Tat
    -0.50
     cut
    -0.50
    헌
    -0.50
     strategy
    -0.47
     Sebastián
    -0.47
    aryan
    -0.47
     target
    -0.47
     ISI
    -0.47
     extensions
    -0.47
    POSITIVE LOGITS
    AsUp
    0.68
    Chham
    0.66
    ConstraintMaker
    0.57
    uxxxx
    0.56
    fromnode
    0.56
    Derbyniad
    0.53
     صوتيه
    0.53
     verksamhet
    0.53
    Captor
    0.52
     vérit
    0.52
    Activations Density 0.014%

    No Known Activations