© 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. 540
    Prev
    Next
    INDEX
    Explanations

    Encyclopaedia/reference material

    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
     take
    -0.41
     only
    -0.37
     her
    -0.36
     like
    -0.36
     K
    -0.35
     taking
    -0.35
    te
    -0.35
     pot
    -0.34
     set
    -0.34
     to
    -0.34
    POSITIVE LOGITS
    SourceChecksum
    0.92
    berdayakan
    0.77
     resourceCulture
    0.75
     ―――――
    0.72
     pédagogique
    0.71
    tvguidetime
    0.71
    Espèce
    0.71
     lenker
    0.70
    ########.
    0.70
    adaptiveStyles
    0.70
    Activations Density 0.001%

    No Known Activations