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. 0-CLT-HP
    4. 44692
    Prev
    Next
    INDEX
    Explanations

    conform

    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
     song
    -0.89
    song
    -0.89
     Hall
    -0.84
     hall
    -0.77
    hall
    -0.75
    Hall
    -0.74
    songs
    -0.72
     songs
    -0.68
     Finch
    -0.67
    ed
    -0.66
    POSITIVE LOGITS
     houſe
    0.76
     ſta
    0.70
     ſche
    0.67
     purpoſe
    0.65
     faſt
    0.62
     Nimbus
    0.61
     étoient
    0.61
     Jefus
    0.61
     ſtate
    0.61
     pleaſure
    0.61
    Activations Density 0.106%

    No Known Activations