© 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. 40054
    Prev
    Next
    INDEX
    Explanations

    Lazar

    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
    ']?>
    -0.68
     Lazar
    -0.66
     الحره
    -0.66
    ++
    -0.64
     مرئيه
    -0.62
    abestanden
    -0.60
    sidemargin
    -0.59
     Lazarus
    -0.58
    NewUrlParser
    -0.58
    GEBURTSDATUM
    -0.58
    POSITIVE LOGITS
    ParallelGroup
    0.61
    ibilité
    0.53
    ovej
    0.48
    Durée
    0.48
     بان
    0.47
     cauliflower
    0.47
    holder
    0.47
     gardener
    0.47
    ely
    0.46
    over
    0.46
    Activations Density 1.710%

    No Known Activations