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. 337
    Prev
    Next
    INDEX
    Explanations

    said/says

    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
     myſelf
    -1.16
    ſelves
    -1.11
     Majefty
    -1.09
     itſelf
    -1.07
    ſelf
    -1.06
     raiſ
    -1.03
     NDEBUG
    -0.99
     doubtnut
    -0.99
     Efq
    -0.98
     himſelf
    -0.95
    POSITIVE LOGITS
    "
    1.15
    ".
    1.05
    ",
    1.02
     "
    1.00
    ")
    0.94
    ."
    0.92
    “
    0.91
    ”
    0.87
    ”.
    0.87
    ").
    0.86
    Activations Density 0.066%

    No Known Activations