© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96813
    Prev
    Next
    INDEX
    Explanations

    navigating

    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
     contextLoads
    -0.60
    pushFollow
    -0.56
    complexType
    -0.54
     Forumite
    -0.54
    jsonwebtoken
    -0.54
    EFAULT
    -0.52
    apatilla
    -0.50
    Smarty
    -0.50
     USB
    -0.49
    setCellStyle
    -0.49
    POSITIVE LOGITS
    \}\\
    0.50
    OCCURRED
    0.47
    offrir
    0.46
     Becken
    0.46
     varian
    0.46
    unt
    0.45
    rawa
    0.44
     Moines
    0.44
    concepto
    0.43
     certaine
    0.42
    Activations Density 0.000%

    No Known Activations