© 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. 10101
    Prev
    Next
    INDEX
    Explanations

    scientific and legal texts

    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
    ade
    -0.65
    UnsafeEnabled
    -0.47
    yakarta
    -0.46
    Dtor
    -0.45
    InSection
    -0.45
    Ade
    -0.45
    ============
    -0.45
     Tunisie
    -0.45
     JpaRepository
    -0.44
     wireType
    -0.43
    POSITIVE LOGITS
    Numerology
    0.63
    ably
    0.58
     ulang
    0.57
    verständlich
    0.55
    issory
    0.54
    radora
    0.54
    ently
    0.53
    Diweddarwch
    0.53
    Chham
    0.52
    claimer
    0.51
    Activations Density 0.023%

    No Known Activations