© 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. 0-CLT-HP
    4. 38905
    Prev
    Next
    INDEX
    Explanations

    software and licensing

    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
    #+#
    -0.58
     épis
    -0.56
     varandra
    -0.56
    клопе
    -0.55
     espagne
    -0.55
     stället
    -0.54
     démo
    -0.53
    SceneManagement
    -0.51
     jadx
    -0.49
     eenige
    -0.48
    POSITIVE LOGITS
     by
    0.76
     with
    0.50
    dellín
    0.50
    isContained
    0.49
    .#
    0.47
     CardView
    0.47
     WorldCat
    0.47
     oleh
    0.46
    outWeight
    0.46
     tet
    0.45
    Activations Density 0.111%

    No Known Activations