© 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. 1-CLT-HP
    7. 10645
    Prev
    Next
    INDEX
    Explanations

    floor

    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
     floor
    -1.52
     Floor
    -1.44
    Floor
    -1.34
     FLOOR
    -1.32
     floors
    -1.30
    FLOOR
    -1.17
    floor
    -1.15
     Floors
    -1.11
    floors
    -0.99
     flooring
    -0.89
    POSITIVE LOGITS
    las
    0.56
    code
    0.54
    lock
    0.53
    paq
    0.53
    ring
    0.51
    top
    0.50
    pan
    0.50
    burn
    0.50
    port
    0.50
    con
    0.50
    Activations Density 0.036%

    No Known Activations