© 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. 1-CLT-HP
    7. 478
    Prev
    Next
    INDEX
    Explanations

    particular

    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
     colour
    -0.64
    colour
    -0.64
    Colour
    -0.63
    ized
    -0.62
     color
    -0.59
     учё
    -0.57
     behavior
    -0.57
     behaviour
    -0.56
     CENTRE
    -0.56
    color
    -0.54
    POSITIVE LOGITS
    expandindo
    0.81
    uxxxx
    0.81
    はじめに
    0.76
    хьтан
    0.75
     HttpNotFound
    0.64
    Rohy
    0.64
    Autoritní
    0.63
    kolen
    0.63
     dAtA
    0.63
     beginnetje
    0.62
    Activations Density 0.021%

    No Known Activations