© 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. 747
    Prev
    Next
    INDEX
    Explanations

    Code and common words

    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
    AutoScaleMode
    -0.92
    IContainer
    -0.84
    MigrationBuilder
    -0.82
    DockStyle
    -0.80
     EconPapers
    -0.77
    تقاوى
    -0.77
    Autoritní
    -0.77
    TagMode
    -0.76
    oa̍t
    -0.75
    RegistryLite
    -0.72
    POSITIVE LOGITS
    encodeWith
    0.42
    Alla
    0.40
    HCM
    0.39
     Milky
    0.39
    devise
    0.38
    Clik
    0.38
    SEO
    0.36
    ggen
    0.36
    ιβ
    0.35
    hw
    0.35
    Activations Density 0.001%

    No Known Activations