© 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. 3348
    Prev
    Next
    INDEX
    Explanations

    Diverse contexts

    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
    -0.51
    ees
    -0.51
    Affirmed
    -0.50
     Grimal
    -0.50
     wax
    -0.50
     Freund
    -0.49
     freeze
    -0.47
    gnostic
    -0.47
     counseling
    -0.47
     waxing
    -0.46
    POSITIVE LOGITS
    +#+#
    0.71
     ExecuteAsync
    0.70
    RectangleBorder
    0.70
    AnchorStyles
    0.69
     automatiques
    0.62
     يتيمه
    0.60
     moyens
    0.59
     générations
    0.59
    tawesome
    0.57
    httphttps
    0.57
    Activations Density 0.003%

    No Known Activations