© 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. 20-CLT-HP
    7. 74618
    Prev
    Next
    INDEX
    Explanations

    percentages

    np_max-act-logits · 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
    BASEPATH
    -0.66
     متعلقه
    -0.59
    Geplaatst
    -0.57
     ExecuteAsync
    -0.57
    findpost
    -0.55
    diocese
    -0.54
     SqlCommand
    -0.53
    anderen
    -0.53
    eabouts
    -0.52
    ||}
    -0.52
    POSITIVE LOGITS
     Administrativna
    0.52
     faccia
    0.50
     transfieras
    0.48
     réglable
    0.47
    DispatchToProps
    0.47
     titolata
    0.47
     coû
    0.46
     volontaire
    0.45
     foncé
    0.45
    ParallelGroup
    0.44
    Activations Density 0.004%

    No Known Activations