© 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. 9434
    Prev
    Next
    INDEX
    Explanations

    user experience

    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
     Adela
    -0.50
    rån
    -0.49
    LessThan
    -0.48
     Penh
    -0.48
    ceptives
    -0.47
    involved
    -0.46
     fler
    -0.45
    aterin
    -0.45
    rowsiness
    -0.44
    Биография
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.65
    IntoConstraints
    0.63
    complexContent
    0.61
     Commencez
    0.61
    setopt
    0.56
     ModelExpression
    0.55
    DataSnapshot
    0.54
     privées
    0.54
     JAXB
    0.52
    TagHelper
    0.51
    Activations Density 0.023%

    No Known Activations