© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 298
    Prev
    Next
    INDEX
    Explanations

    time adverbs

    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
     legal
    -0.48
    はじめに
    -0.47
     mandatory
    -0.46
    LookAnd
    -0.45
    :+:
    -0.44
     تضيفلها
    -0.44
     inter
    -0.42
     CascadeType
    -0.42
     final
    -0.40
    itson
    -0.40
    POSITIVE LOGITS
    onAttach
    0.77
     servici
    0.57
    mapStateToProps
    0.57
    jws
    0.57
     InputDecoration
    0.57
    :]:
    0.56
    Vendo
    0.56
     înc
    0.56
    ureusement
    0.55
    :][
    0.54
    Activations Density 1.493%

    No Known Activations