© 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. 4-CLT-HP
    4. 3393
    Prev
    Next
    INDEX
    Explanations

    world

    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
     mijne
    -0.60
    enetrable
    -0.53
     oignons
    -0.52
    ந
    -0.52
    iores
    -0.52
     femininas
    -0.52
     وحد
    -0.50
    dhist
    -0.50
    tät
    -0.50
     giới
    -0.49
    POSITIVE LOGITS
    BeginContext
    0.68
    +#+#
    0.60
    httphttps
    0.59
     Thesaurus
    0.58
     halla
    0.57
    তথ্যসূত্র
    0.56
    RectangleBorder
    0.54
    AutoScaleMode
    0.53
    IntoConstraints
    0.52
    $_['
    0.51
    Activations Density 0.001%

    No Known Activations