© 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. 5-CLT-HP
    7. 92107
    Prev
    Next
    INDEX
    Explanations

    at

    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
    Diwedd
    -0.65
    edar
    -0.47
     exposure
    -0.46
     conventional
    -0.46
     deforma
    -0.46
    rrggbb
    -0.45
     IEnumerator
    -0.45
     homolog
    -0.45
    ông
    -0.45
     present
    -0.45
    POSITIVE LOGITS
     Normdatei
    0.68
    nestjs
    0.61
    Brainz
    0.60
     about
    0.60
    MLLoader
    0.60
    tidaknya
    0.57
     terang
    0.55
    posedge
    0.55
    AddTagHelper
    0.55
    rungsseite
    0.54
    Activations Density 0.005%

    No Known Activations