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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94752
    Prev
    Next
    INDEX
    Explanations

    variation

    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
    fjspx
    -0.70
     invokingState
    -0.69
     GenerationType
    -0.67
    TagMode
    -0.57
     WaitForSeconds
    -0.54
    InjectAttribute
    -0.53
    Geplaatst
    -0.53
     variations
    -0.52
    extAlignment
    -0.52
     simplifié
    -0.50
    POSITIVE LOGITS
     Argonne
    0.62
    cience
    0.61
     electrons
    0.60
     Langmuir
    0.57
     cohomology
    0.57
     Morality
    0.57
     glau
    0.57
     Telescope
    0.56
     CERN
    0.56
    richten
    0.55
    Activations Density 0.454%

    No Known Activations