© 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. 4840
    Prev
    Next
    INDEX
    Explanations

    signal processing/engineering

    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
    tagHelperRunner
    -1.04
     kasarigan
    -1.02
    StoryboardSegue
    -0.90
    Lähteet
    -0.88
     ainfi
    -0.84
     HasFactory
    -0.83
    DoubleQuotes
    -0.81
    Hozzáférés
    -0.78
     unknownFields
    -0.78
    __':
    -0.77
    POSITIVE LOGITS
     word
    0.52
     term
    0.50
     eye
    0.49
    word
    0.48
     executive
    0.45
     En
    0.45
     estimate
    0.44
     estimates
    0.44
     history
    0.44
     PRO
    0.43
    Activations Density 0.003%

    No Known Activations