© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92862
    Prev
    Next
    INDEX
    Explanations

    moderate

    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
    moderate
    -1.55
     moderate
    -1.46
    Moderate
    -1.39
     Moderate
    -1.34
     moder
    -1.08
    moder
    -1.08
    Moder
    -1.00
     Moderately
    -1.00
     moderately
    -0.96
     '\\;'
    -0.89
    POSITIVE LOGITS
    est
    0.50
    ly
    0.48
    ieR
    0.44
     actual
    0.44
     authority
    0.42
     apparent
    0.42
     U
    0.41
     Authority
    0.41
     Baillargeon
    0.41
     O
    0.40
    Activations Density 0.190%

    No Known Activations