© 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. 96206
    Prev
    Next
    INDEX
    Explanations

    help

    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
    AndroidJUnit
    -0.52
    NotSupported
    -0.51
    msgSender
    -0.51
    gridy
    -0.49
     CWE
    -0.48
     canali
    -0.47
    chaun
    -0.47
    quels
    -0.47
    Rhestr
    -0.46
    troppo
    -0.46
    POSITIVE LOGITS
    
    0.74
    head
    0.63
     noDo
    0.60
     يتيمه
    0.58
     '\\;'
    0.56
    DockStyle
    0.55
    帖最后由
    0.54
    uesia
    0.52
    state
    0.50
    WebElementEntity
    0.50
    Activations Density 0.005%

    No Known Activations