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. 39150
    Prev
    Next
    INDEX
    Explanations

    umal

    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
     you
    -1.39
     your
    -1.02
     itſelf
    -1.01
     ſtate
    -0.96
     houſe
    -0.94
     pleaſure
    -0.94
     faſt
    -0.93
     ſche
    -0.91
     myſelf
    -0.90
     ſta
    -0.88
    POSITIVE LOGITS
     are
    0.77
    ’
    0.66
    '
    0.60
     were
    0.60
     can
    0.60
     have
    0.54
     had
    0.54
     grew
    0.53
    眸
    0.53
     will
    0.52
    Activations Density 1.824%

    No Known Activations