© 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. 1084
    Prev
    Next
    INDEX
    Explanations

    normal

    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
    oredCriteria
    -0.82
     متعلقه
    -0.74
     صوتيه
    -0.67
     referenties
    -0.66
    StoryboardSegue
    -0.64
    GraphicsUnit
    -0.64
     dimensione
    -0.61
    Jîn
    -0.59
     Exactos
    -0.56
     lunghezza
    -0.56
    POSITIVE LOGITS
     مشين
    0.54
     and
    0.54
    yce
    0.43
    issimi
    0.42
    verständlich
    0.40
    databind
    0.39
    ibatis
    0.39
     Asunción
    0.39
    RetentionPolicy
    0.39
     citron
    0.38
    Activations Density 0.004%

    No Known Activations