© 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. 0-CLT-HP
    7. 1078
    Prev
    Next
    INDEX
    Explanations

    human

    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
     étoit
    -0.61
    LabelTagHelper
    -0.60
     présentés
    -0.59
     complètes
    -0.59
    ammans
    -0.58
     Efq
    -0.56
     onwards
    -0.56
     genoemd
    -0.55
     stratégique
    -0.54
     auroit
    -0.54
    POSITIVE LOGITS
    ity
    1.54
    ities
    1.38
    itarian
    1.05
    s
    1.04
    ITY
    1.02
    es
    0.93
    itys
    0.90
    ات
    0.79
    țional
    0.73
    ist
    0.67
    Activations Density 0.022%

    No Known Activations