© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    one

    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
     ligiloj
    -0.75
    Personendaten
    -0.71
     cherchés
    -0.70
     disponibilités
    -0.69
     createSlice
    -0.69
    matchCondition
    -0.68
    featureID
    -0.68
     pinulongan
    -0.67
    TypedDataSet
    -0.66
     الرياضيه
    -0.66
    POSITIVE LOGITS
     sense
    0.58
     respect
    0.54
     place
    0.52
     noted
    0.45
     celebrated
    0.44
     fell
    0.44
     telling
    0.44
     well
    0.43
     study
    0.42
    sense
    0.42
    Activations Density 0.001%

    No Known Activations