© 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. 0-CLT-HP
    7. 38743
    Prev
    Next
    INDEX
    Explanations

    preposition

    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
     ModelExpression
    -0.84
     autorytatywna
    -0.73
    HideFlags
    -0.71
    ValueStyle
    -0.70
    verwijspagina
    -0.70
    TagMode
    -0.69
     kasarigan
    -0.68
    MockBean
    -0.68
    RUnlock
    -0.67
    SourceChecksum
    -0.66
    POSITIVE LOGITS
    ories
    0.49
    =',
    0.48
    ota
    0.47
    )['
    0.46
    ary
    0.44
    arel
    0.43
    ert
    0.43
    tas
    0.42
     lega
    0.42
     incorpora
    0.41
    Activations Density 0.692%

    No Known Activations