© 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. 2176
    Prev
    Next
    INDEX
    Explanations

    to

    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
    forKey
    -0.60
    PerformLayout
    -0.56
     setError
    -0.54
    ImGui
    -0.52
     inflater
    -0.50
    <>("
    -0.50
     uintptr
    -0.50
    mybatisplus
    -0.49
     forKey
    -0.48
    CCER
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.63
    hoebe
    0.58
     Either
    0.57
     chargés
    0.57
    either
    0.55
    也好
    0.55
    Either
    0.53
     Such
    0.53
     Réponses
    0.52
     romanos
    0.52
    Activations Density 0.001%

    No Known Activations