© 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. 1-CLT-HP
    7. 14959
    Prev
    Next
    INDEX
    Explanations

    pretreatment

    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
     prepaid
    -0.73
     '\\;'
    -0.69
    conium
    -0.69
     كومونز
    -0.66
     Prepaid
    -0.62
    aarrggbb
    -0.59
    HomeAsUpEnabled
    -0.57
    Спасылкі
    -0.56
    HtmlAttribute
    -0.56
    GeneratedValue
    -0.56
    POSITIVE LOGITS
    iness
    0.61
     nakalista
    0.58
     Boug
    0.57
    èges
    0.55
     Clever
    0.54
     Oops
    0.53
     Bugs
    0.53
    /******/
    0.53
     Buggy
    0.53
     TQ
    0.52
    Activations Density 0.032%

    No Known Activations