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. 20-CLT-HP
    4. 74091
    Prev
    Next
    INDEX
    Explanations

    Random, varied texts

    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
    -0.60
    #+#
    -0.56
     ***!
    -0.55
    rungsseite
    -0.55
     Oro
    -0.55
    InitVars
    -0.54
     Roskov
    -0.53
    rawtypes
    -0.53
     Moist
    -0.51
    んぼ
    -0.51
    POSITIVE LOGITS
    出版年
    0.60
     kasarigan
    0.49
     Sunak
    0.46
    gangssprach
    0.46
    gdx
    0.44
    ransition
    0.42
    ProgressHUD
    0.41
    makeText
    0.41
     inni
    0.41
     st
    0.40
    Activations Density 0.000%

    No Known Activations