© 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. 135
    Prev
    Next
    INDEX
    Explanations

    other

    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
    migrationBuilder
    -0.88
    Espèce
    -0.78
     Ause
    -0.77
    phrine
    -0.76
    ">—
    -0.73
    تقاوى
    -0.73
    rungsseite
    -0.71
     CascadeType
    -0.69
    BASEPATH
    -0.69
     verwijzen
    -0.68
    POSITIVE LOGITS
     metrics
    0.40
     concepts
    0.39
    ArgsConstructor
    0.37
     quantities
    0.37
     hypothetical
    0.36
     summary
    0.35
     story
    0.35
     måske
    0.34
     principles
    0.34
     phenomena
    0.33
    Activations Density 0.002%

    No Known Activations