© 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. 20-CLT-HP
    7. 74487
    Prev
    Next
    INDEX
    Explanations

    August

    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
     imageNamed
    -0.63
     Oct
    -0.60
    Oct
    -0.57
     ['./
    -0.54
    JoinColumn
    -0.52
    __(/*!
    -0.52
     Stelle
    -0.52
    ніципалі
    -0.51
    atically
    -0.50
    Sept
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.60
     autorytatywna
    0.49
    loài
    0.45
    الحياه
    0.45
     MenuView
    0.45
    inians
    0.43
    lblNewLabel
    0.42
    Alo
    0.42
     rhestr
    0.42
     Alo
    0.41
    Activations Density 0.002%

    No Known Activations