Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12421
    Prev
    Next
    INDEX
    Explanations

    rate

    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
     تضيفلها
    -0.93
     Normdatei
    -0.91
     Efq
    -0.90
     <<<<<<<<<<<<<<
    -0.90
     Савезне
    -0.86
     ſeveral
    -0.85
    RenderAtEndOf
    -0.85
     pleaſure
    -0.85
     houſe
    -0.84
     whoſe
    -0.84
    POSITIVE LOGITS
     (
    0.42
     Boy
    0.39
     boy
    0.38
     di
    0.36
     z
    0.35
    uli
    0.34
     I
    0.34
     tup
    0.34
     of
    0.34
    ul
    0.33
    Activations Density 0.045%

    No Known Activations