© 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. 0-CLT-HP
    7. 1338
    Prev
    Next
    INDEX
    Explanations

    imi

    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
     clear
    -0.79
     strip
    -0.56
     too
    -0.53
    clear
    -0.53
    дравству
    -0.52
     المتحدة
    -0.51
    IMI
    -0.50
     Clear
    -0.49
    daki
    -0.48
     Strip
    -0.47
    POSITIVE LOGITS
    principalTable
    0.68
     <<<<<<<<<<<<<<
    0.67
    aarrggbb
    0.65
    isseur
    0.64
    CloseOperation
    0.63
     tuc
    0.62
     &___
    0.61
     Unwin
    0.59
    jenner
    0.59
    })`
    0.58
    Activations Density 0.043%

    No Known Activations