© 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. 5-CLT-HP
    7. 92233
    Prev
    Next
    INDEX
    Explanations

    speed or urgency

    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
    HL
    -0.47
    brid
    -0.43
    CppMethod
    -0.42
    uw
    -0.41
    alt
    -0.41
    abs
    -0.40
    izin
    -0.40
    addCriterion
    -0.40
    SerializeField
    -0.40
    Brid
    -0.39
    POSITIVE LOGITS
     esboço
    0.73
    adaptiveStyles
    0.72
     internetowa
    0.70
    XmlAccessType
    0.69
    !*\
    0.68
     lentement
    0.68
    Czytaj
    0.65
     onOptions
    0.64
    Izvori
    0.63
    bootstrapcdn
    0.63
    Activations Density 0.006%

    No Known Activations