Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3981
    Prev
    Next
    INDEX
    Explanations

    Clicking/Tapping

    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
     the
    -0.62
     a
    -0.52
    specialchars
    -0.49
    jboss
    -0.46
    ()].
    -0.41
    TypedDataSet
    -0.41
    isse
    -0.41
    ity
    -0.40
    
    
    -0.39
     this
    -0.39
    POSITIVE LOGITS
     بيها
    0.71
     dàng
    0.68
     itſelf
    0.64
     raiſ
    0.63
    DockStyle
    0.60
     Ordering
    0.59
    artamento
    0.59
     faſt
    0.59
     ordering
    0.59
     ſte
    0.59
    Activations Density 0.002%

    No Known Activations