© 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. 96114
    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
    ۇ
    -0.59
     hiér
    -0.59
     Infórmanos
    -0.58
    PreExecute
    -0.58
     popoli
    -0.58
    Demografía
    -0.58
    TypedDataSet
    -0.58
    ometrica
    -0.57
     CreateTagHelper
    -0.57
    brew
    -0.57
    POSITIVE LOGITS
     Either
    0.49
    Either
    0.49
    Captor
    0.43
    ')));
    0.42
    ีม
    0.41
    '])->
    0.41
    AsUp
    0.40
    ętr
    0.40
     either
    0.40
    either
    0.40
    Activations Density 0.002%

    No Known Activations