© 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. 0-CLT-HP
    7. 44221
    Prev
    Next
    INDEX
    Explanations

    verbal

    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
     nakalista
    -0.93
    hot
    -0.88
     Matter
    -0.85
    hogs
    -0.81
    hots
    -0.80
    HOT
    -0.74
    PropertyChanging
    -0.74
    <()>
    -0.71
     hot
    -0.71
    hopper
    -0.68
    POSITIVE LOGITS
    ness
    0.52
    en
    0.45
    cleros
    0.41
    2
    0.41
    ואר
    0.40
    ity
    0.39
    auw
    0.39
    1
    0.39
    3
    0.39
    arkas
    0.38
    Activations Density 0.108%

    No Known Activations