© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 324
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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
    ć
    -0.81
    +:+
    -0.75
    ftagPool
    -0.72
     chun
    -0.69
    Geplaatst
    -0.68
    TagHelpers
    -0.64
     InputDecoration
    -0.63
    httphttps
    -0.62
    TRAILING
    -0.61
     Chun
    -0.60
    POSITIVE LOGITS
    mybatisplus
    0.49
    niec
    0.47
     Mar
    0.42
    kym
    0.41
     real
    0.39
    pec
    0.39
     निक
    0.38
    Референце
    0.38
    omnia
    0.37
    DoubleQuotes
    0.37
    Activations Density 0.066%

    No Known Activations