© 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. 90936
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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
     referenties
    -0.60
     overlaps
    -0.58
     overlap
    -0.57
     tweet
    -0.55
     permissions
    -0.54
     tweets
    -0.53
    UnknownFieldSet
    -0.51
     surprises
    -0.50
     comparisons
    -0.50
     capacities
    -0.50
    POSITIVE LOGITS
    IntoConstraints
    0.66
     espirituales
    0.65
     vectoriales
    0.63
     deportivos
    0.63
     iniciales
    0.58
     käytet
    0.57
     necessárias
    0.57
     seguras
    0.57
     BorderRadius
    0.57
     caratteri
    0.57
    Activations Density 0.016%

    No Known Activations