© 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. 20-CLT-HP
    4. 74530
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    TagMode
    -0.81
    verwijspagina
    -0.81
     doInBackground
    -0.78
     мәкал
    -0.75
     kasarigan
    -0.74
    ConstraintMaker
    -0.69
    Portail
    -0.68
    HtmlAttribute
    -0.68
    invokeLater
    -0.66
    IntoConstraints
    -0.66
    POSITIVE LOGITS
     فريبيس
    0.51
     imageNamed
    0.41
     prolon
    0.40
    mpto
    0.39
    üz
    0.39
     تضيفلها
    0.39
     protons
    0.38
     Trie
    0.37
     pist
    0.36
     alphabetically
    0.36
    Activations Density 0.000%

    No Known Activations