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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4522
    Prev
    Next
    INDEX
    Explanations

    complex technical topics

    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
     NSCoder
    -0.79
    帖最后由
    -0.75
     AssemblyVersion
    -0.74
     للمعارف
    -0.67
     للاسماء
    -0.64
     <=",
    -0.61
    SourceChecksum
    -0.61
    +#+#
    -0.59
    ArrowToggle
    -0.59
    OGND
    -0.58
    POSITIVE LOGITS
    /
    0.53
    agal
    0.47
    formik
    0.46
     gre
    0.46
    rolls
    0.45
    λία
    0.44
    GPP
    0.43
     pii
    0.43
     bru
    0.43
    -
    0.43
    Activations Density 0.003%

    No Known Activations