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. 97921
    Prev
    Next
    INDEX
    Explanations

    code

    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
    d
    -0.90
    p
    -0.89
    k
    -0.88
    f
    -0.85
    A
    -0.82
    b
    -0.81
    S
    -0.79
    T
    -0.79
    g
    -0.79
    m
    -0.78
    POSITIVE LOGITS
    ^(@)
    1.23
    esterday
    1.14
    BibitemShut
    1.09
    bibfield
    1.07
    bibinfo
    1.05
    ENEFITS
    1.02
    IBLIO
    1.01
     nakalista
    1.01
    frastructure
    0.99
    ugeot
    0.98
    Activations Density 0.495%

    No Known Activations