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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42283
    Prev
    Next
    INDEX
    Explanations

    computer interfaces

    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
     مرئيه
    -0.95
    ſelves
    -0.77
     themſelves
    -0.75
     himſelf
    -0.74
     виправивши
    -0.73
     itſelf
    -0.73
     houſe
    -0.71
     myſelf
    -0.70
    ſelf
    -0.69
     raiſ
    -0.69
    POSITIVE LOGITS
    riwal
    0.50
    디
    0.50
    mtd
    0.45
    s
    0.44
    RunAsync
    0.44
    Execute
    0.43
    omu
    0.42
     mes
    0.41
     ve
    0.41
    jsxFileName
    0.41
    Activations Density 0.942%

    No Known Activations