© 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. 12531
    Prev
    Next
    INDEX
    Explanations

    Large scale data/yields

    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
     ostavi
    -1.01
     propOrder
    -0.75
    StoryboardSegue
    -0.74
    BeforeAll
    -0.70
    WebElementEntity
    -0.67
     doInBackground
    -0.64
    ScopeManager
    -0.63
    BeforeClass
    -0.61
    WireFormat
    -0.58
    AsyncResult
    -0.57
    POSITIVE LOGITS
     AMS
    0.44
    ).
    0.41
     enhancement
    0.41
     autonomy
    0.41
    urante
    0.40
    ónima
    0.40
     AGB
    0.40
    ainya
    0.40
     dispensation
    0.40
    fay
    0.39
    Activations Density 0.010%

    No Known Activations