© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91149
    Prev
    Next
    INDEX
    Explanations

    space and age

    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
     moons
    -1.15
    moons
    -0.93
     younger
    -0.90
     Younger
    -0.73
     Moons
    -0.72
    Moons
    -0.69
    Younger
    -0.65
    introduction
    -0.57
    an
    -0.54
    moon
    -0.54
    POSITIVE LOGITS
    XmlAccessType
    0.73
     sympy
    0.61
    esez
    0.60
     Réponses
    0.57
    makeConstraints
    0.56
    ridos
    0.55
    setopt
    0.55
     Zeugen
    0.54
    Enllaces
    0.54
     Référence
    0.53
    Activations Density 0.750%

    No Known Activations