© 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. 20-CLT-HP
    7. 76596
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · 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
     betweenstory
    -0.60
     repeater
    -0.59
     kaarangay
    -0.57
    הערות
    -0.57
     crawler
    -0.53
     wobble
    -0.53
    Prediction
    -0.52
     aprons
    -0.52
    #}
    -0.52
     bowled
    -0.51
    POSITIVE LOGITS
    mybatisplus
    0.50
    ForValue
    0.48
    CrossRef
    0.48
    persky
    0.47
    xbc
    0.46
     مشين
    0.46
    laim
    0.45
    يند
    0.44
     Tortoise
    0.44
     Oasis
    0.44
    Activations Density 0.002%

    No Known Activations