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. 5-CLT-HP
    4. 95374
    Prev
    Next
    INDEX
    Explanations

    or

    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
     الحره
    -0.81
    MLLoader
    -0.77
    )‏
    -0.71
    providedIn
    -0.70
     оригіналу
    -0.69
    contentLoaded
    -0.68
    VolleyError
    -0.68
    httphttps
    -0.67
     للاسماء
    -0.66
    NamedQueries
    -0.66
    POSITIVE LOGITS
     anche
    0.57
     "
    0.54
     both
    0.54
     and
    0.50
     '
    0.49
     non
    0.48
     &
    0.47
    :
    0.47
     auch
    0.46
     Both
    0.46
    Activations Density 0.008%

    No Known Activations