© 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. 5-CLT-HP
    7. 1946
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    HtmlAttribute
    -0.60
    évaluateur
    -0.56
    RegressionTest
    -0.54
    extAlignment
    -0.54
    arrings
    -0.54
    usermodel
    -0.54
    CloseOperation
    -0.52
    sunami
    -0.52
    Reprints
    -0.51
    REVIEWS
    -0.51
    POSITIVE LOGITS
    com
    0.67
    most
    0.62
    rd
    0.61
    pop
    0.56
    como
    0.55
    >--}}
    0.54
    ner
    0.54
    p
    0.54
    best
    0.53
    low
    0.52
    Activations Density 0.042%

    No Known Activations