© 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. 42357
    Prev
    Next
    INDEX
    Explanations

    reliable

    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
    Tell
    -0.76
     tell
    -0.66
     telling
    -0.64
    Pyx
    -0.61
     Telling
    -0.60
     reliable
    -0.60
    tell
    -0.57
     Tell
    -0.57
     rencontr
    -0.57
     geldig
    -0.55
    POSITIVE LOGITS
    ValueStyle
    0.82
     estimés
    0.68
    AccessorTable
    0.63
     EconPapers
    0.61
     tartalomajánló
    0.60
    principalTable
    0.59
     ControllerBase
    0.55
     sessile
    0.53
     alkaline
    0.52
    %</
    0.52
    Activations Density 1.578%

    No Known Activations