© 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. 0-CLT-HP
    7. 40969
    Prev
    Next
    INDEX
    Explanations

    women

    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
    存于互联网档案馆
    -0.68
    Hochspringen
    -0.64
     ProtoMessage
    -0.64
    homonymie
    -0.58
    ContentAsync
    -0.54
     lenker
    -0.53
    Viitteet
    -0.52
    cydow
    -0.52
     snippetHide
    -0.51
    ̍t
    -0.51
    POSITIVE LOGITS
    addPreferredGap
    0.61
    migrationBuilder
    0.59
     monitored
    0.56
    FormState
    0.53
     crushed
    0.50
     administering
    0.48
     diagnosed
    0.48
     centrifuged
    0.48
     WebDriverWait
    0.47
    hasMoreElements
    0.47
    Activations Density 0.176%

    No Known Activations