© 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. 12181
    Prev
    Next
    INDEX
    Explanations

    pron

    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
    pron
    -0.66
    Pron
    -0.65
    haga
    -0.58
     prompt
    -0.54
    cade
    -0.50
    rases
    -0.49
    RIED
    -0.47
     Kalt
    -0.47
     Pron
    -0.47
     Vivid
    -0.47
    POSITIVE LOGITS
    adpleegd
    0.68
    enumi
    0.66
     BrowserModule
    0.66
    ouns
    0.65
     Roskov
    0.65
    unci
    0.63
     kaynağından
    0.61
    SOCK
    0.61
     kaarangay
    0.59
    ounce
    0.58
    Activations Density 0.075%

    No Known Activations