© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45896
    Prev
    Next
    INDEX
    Explanations

    narrative/stories

    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
     pinulongan
    -0.66
    MigrationBuilder
    -0.51
     lenker
    -0.49
     tell
    -0.47
     nonatomic
    -0.45
    Gweler
    -0.44
     tale
    -0.42
     storytelling
    -0.41
     GetEnumerator
    -0.41
     share
    -0.41
    POSITIVE LOGITS
     astronomers
    0.76
     mathematicians
    0.69
     allu
    0.66
     nymphs
    0.66
     prophylaxis
    0.66
     cerebellar
    0.66
     terrorists
    0.66
    ruptedException
    0.65
     houſe
    0.63
     clinicians
    0.62
    Activations Density 0.004%

    No Known Activations