© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43782
    Prev
    Next
    INDEX
    Explanations

    matter

    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
     matter
    -4.25
    matter
    -3.36
     MATTER
    -2.92
     Matter
    -2.78
    Matter
    -2.73
     matters
    -2.28
     mattered
    -2.06
    matters
    -2.02
    Matters
    -1.81
     Matters
    -1.74
    POSITIVE LOGITS
    ing
    0.81
     to
    0.68
     of
    0.64
     in
    0.58
     from
    0.58
     if
    0.57
     that
    0.57
     with
    0.54
     for
    0.53
     which
    0.51
    Activations Density 0.025%

    No Known Activations