© 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. 95201
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     to
    -0.55
    endpush
    -0.50
    RTGC
    -0.50
     municipales
    -0.49
     effetto
    -0.49
     crescere
    -0.48
     einen
    -0.48
     zu
    -0.47
    Josef
    -0.47
    !("
    -0.46
    POSITIVE LOGITS
    Datuak
    0.63
     Meksiku
    0.56
    StoryboardSegue
    0.54
     وتسجيلات
    0.54
     GenerationType
    0.52
     للمعارف
    0.51
    ContentAsync
    0.50
    SequentialGroup
    0.50
    etheless
    0.49
    enosine
    0.48
    Activations Density 0.004%

    No Known Activations