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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74585
    Prev
    Next
    INDEX
    Explanations

    Lowercase then uppercase letters

    np_max-act-logits · 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
     kaarangay
    -0.72
     виправивши
    -0.67
     esternos
    -0.66
    :✨
    -0.65
     typelib
    -0.64
     cherchés
    -0.62
    enumii
    -0.56
    NameInMap
    -0.55
    Tikang
    -0.54
    twimg
    -0.52
    POSITIVE LOGITS
    kd
    0.91
    jd
    0.80
    Qd
    0.80
    gd
    0.79
    KD
    0.79
    fd
    0.79
    SFD
    0.79
    sd
    0.77
     KD
    0.77
    bd
    0.76
    Activations Density 0.001%

    No Known Activations