© 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. 501
    Prev
    Next
    INDEX
    Explanations

    direction and procedures

    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
     heading
    -0.62
     headed
    -0.60
    adj
    -0.54
     inter
    -0.54
    Heading
    -0.52
    inter
    -0.51
    extra
    -0.46
    not
    -0.45
    disp
    -0.45
     Heading
    -0.45
    POSITIVE LOGITS
    webElementXpaths
    0.75
     resourceCulture
    0.73
    UnsafeEnabled
    0.72
    ValueGenerated
    0.69
    twimg
    0.67
    sizeCache
    0.66
    Datuak
    0.64
    ArgumentParser
    0.63
    发表于
    0.62
    ativement
    0.61
    Activations Density 0.030%

    No Known Activations