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-GEMMASCOPE-TRANSCODER-16K
    4. 14025
    Prev
    Next
    INDEX
    Explanations

    the word "ball"

    oai_token-act-pair · gemini-2.0-flash

    ball

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstanceState
    -0.62
     Italijanski
    -0.62
    HttpFoundation
    -0.59
    enumi
    -0.57
    IsContent
    -0.56
    OGND
    -0.56
    Trimethyl
    -0.54
    JNIEnv
    -0.54
     BoxFit
    -0.53
     Gegenteil
    -0.52
    POSITIVE LOGITS
     cherchés
    0.59
    
    0.52
    Démographie
    0.51
    gól
    0.48
    '][$
    0.47
    glBindTexture
    0.47
    engar
    0.46
    IVEREF
    0.46
    upati
    0.46
    mètres
    0.46
    Activations Density 2.465%

    No Known Activations