© 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. 4-CLT-HP
    7. 515
    Prev
    Next
    INDEX
    Explanations

    Code and/or illegal activities

    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
     Jefus
    -0.75
     ſtate
    -0.72
     ſeveral
    -0.71
     समीक्षाओं
    -0.69
     myſelf
    -0.69
     ainfi
    -0.67
     ftate
    -0.67
     purpoſe
    -0.66
     chofe
    -0.66
    tvguidetime
    -0.66
    POSITIVE LOGITS
     or
    0.63
     poaching
    0.49
    titleMargin
    0.47
     drug
    0.45
     سبورت
    0.44
     and
    0.43
    InjectAttribute
    0.43
    webElementXpaths
    0.42
    top
    0.42
     SqlCommand
    0.41
    Activations Density 0.001%

    No Known Activations