© 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. 1-CLT-HP
    7. 10385
    Prev
    Next
    INDEX
    Explanations

    Something being "held"

    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
    held
    -0.60
     holding
    -0.56
    ager
    -0.55
    hold
    -0.53
    time
    -0.52
     held
    -0.52
     hold
    -0.51
    an
    -0.50
    IndentedString
    -0.49
    age
    -0.49
    POSITIVE LOGITS
    بوابة
    0.65
    __':
    0.63
     MainAxisSize
    0.61
    Kenmerken
    0.60
    luiting
    0.58
     testify
    0.56
    AddTagHelper
    0.55
    UnknownFields
    0.53
     SearchView
    0.53
    Autoritní
    0.53
    Activations Density 0.106%

    No Known Activations