© 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. 5-CLT-HP
    7. 3298
    Prev
    Next
    INDEX
    Explanations

    the

    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
    InSection
    -0.62
    MessageOf
    -0.60
    AsUp
    -0.60
    können
    -0.58
    gnore
    -0.55
    FormTagHelper
    -0.54
     Klar
    -0.54
    )]$
    -0.53
    ToBounds
    -0.53
     predominance
    -0.53
    POSITIVE LOGITS
    -
    0.56
    head
    0.50
    stand
    0.49
    book
    0.49
     juges
    0.47
    set
    0.46
    star
    0.46
    line
    0.45
    yard
    0.45
    lock
    0.45
    Activations Density 0.010%

    No Known Activations