© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4310
    Prev
    Next
    INDEX
    Explanations

    a

    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
     podamos
    -0.48
     puedas
    -0.44
     cuenta
    -0.44
    AnchorStyles
    -0.44
     possam
    -0.41
     فريبيس
    -0.41
    rawDesc
    -0.41
    aurais
    -0.40
    just
    -0.40
    none
    -0.40
    POSITIVE LOGITS
     Monfieur
    0.78
     Efq
    0.73
     Theſe
    0.72
     ſeveral
    0.65
     ſever
    0.63
     himo
    0.63
     BoxFit
    0.62
    NUMX
    0.62
    MethodManager
    0.61
     BorderSide
    0.60
    Activations Density 0.002%

    No Known Activations