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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3253
    Prev
    Next
    INDEX
    Explanations

    ritis

    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
     SEDS
    -0.65
     onBind
    -0.62
    illoma
    -0.57
    ReusableCell
    -0.55
     Stron
    -0.55
    Hats
    -0.54
    Одно
    -0.54
     ſch
    -0.54
     Plaid
    -0.54
     Automobiles
    -0.53
    POSITIVE LOGITS
    jspx
    0.53
    tagext
    0.52
     ComVisible
    0.52
     complain
    0.52
     <=",
    0.49
    WriteBarrier
    0.47
    baguna
    0.45
    AddTagHelper
    0.45
     acus
    0.45
     denuncias
    0.44
    Activations Density 0.001%

    No Known Activations