© 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. 1-CLT-HP
    7. 798
    Prev
    Next
    INDEX
    Explanations

    statement

    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
     statement
    -0.75
     STATEMENT
    -0.73
    statement
    -0.72
     Statement
    -0.68
    Statement
    -0.64
     declaración
    -0.51
    statements
    -0.51
    נוּ
    -0.50
    info
    -0.49
     déclarations
    -0.46
    POSITIVE LOGITS
    WireFormatLite
    0.92
     Efq
    0.80
    ViewFeatures
    0.74
     CreateTagHelper
    0.74
    )="
    0.71
    thenReturn
    0.70
     otomatig
    0.68
     ―――――
    0.66
     LZ
    0.65
     Theſe
    0.64
    Activations Density 0.014%

    No Known Activations