© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3218
    Prev
    Next
    INDEX
    Explanations

    center

    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
    jsxFileName
    -0.61
     real
    -0.51
    клопе
    -0.49
    webElementXpaths
    -0.49
    thoven
    -0.47
     Crawford
    -0.47
    ptons
    -0.47
    Փ
    -0.46
    tallet
    -0.46
    ritten
    -0.46
    POSITIVE LOGITS
    ThroughAttribute
    0.84
     للمعارف
    0.71
     BoxDecoration
    0.65
    DataAnnotations
    0.63
    glLoadIdentity
    0.60
     avoit
    0.58
     pouvoit
    0.56
     rospy
    0.55
    tvguidetime
    0.55
     étoit
    0.54
    Activations Density 0.006%

    No Known Activations