© 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. 2952
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    yntaxException
    -0.82
     NSCoder
    -0.70
    олові
    -0.65
    RenderAtEndOf
    -0.64
     hâte
    -0.64
    titleMargin
    -0.61
     themſelves
    -0.60
    .*")]
    -0.60
    migrationBuilder
    -0.59
     AttributeSet
    -0.59
    POSITIVE LOGITS
    -
    0.60
    DockStyle
    0.60
    most
    0.50
    ly
    0.49
    del
    0.48
     reaches
    0.48
    est
    0.47
     tip
    0.45
    ale
    0.44
     end
    0.44
    Activations Density 0.003%

    No Known Activations