© 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. 95024
    Prev
    Next
    INDEX
    Explanations

    processed

    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
    tvguidetime
    -1.05
     CreateTagHelper
    -0.85
    WebVitals
    -0.77
    RectangleBorder
    -0.76
    ressee
    -0.72
    VIAF
    -0.71
     للمعارف
    -0.68
    otheses
    -0.68
     betweenstory
    -0.66
    middels
    -0.66
    POSITIVE LOGITS
     form
    0.45
    :
    0.42
     laba
    0.41
    уда
    0.41
     options
    0.40
     hashCode
    0.39
    cader
    0.37
    /*:
    0.37
     &
    0.36
    низ
    0.36
    Activations Density 0.000%

    No Known Activations