© 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. 5-CLT-HP
    7. 95253
    Prev
    Next
    INDEX
    Explanations

    stamped

    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
     Baillargeon
    -0.64
     Мексичка
    -0.63
     Italijani
    -0.62
     noDo
    -0.59
    enumi
    -0.59
    quelize
    -0.58
    ToAction
    -0.57
     naselje
    -0.57
     fieldNum
    -0.56
     MessageBoxIcon
    -0.55
    POSITIVE LOGITS
    Rev
    0.46
    zic
    0.46
    getline
    0.46
    Pit
    0.45
    tanleria
    0.44
    裹
    0.44
     decorations
    0.44
    bole
    0.43
     hom
    0.43
     symbols
    0.43
    Activations Density 0.000%

    No Known Activations