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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93652
    Prev
    Next
    INDEX
    Explanations

    filling

    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
     myſelf
    -0.80
     Efq
    -0.78
     purpoſe
    -0.76
     iſt
    -0.73
     Majefty
    -0.71
    expandindo
    -0.70
     depositphotos
    -0.69
     ſch
    -0.65
     houſe
    -0.65
     Monfieur
    -0.65
    POSITIVE LOGITS
    RegistryLite
    0.73
     newOwner
    0.55
    printStackTrace
    0.55
    TagMode
    0.54
    🧼
    0.46
    saraba
    0.46
     AppModule
    0.45
    SequentialGroup
    0.45
    ⓘ
    0.45
     of
    0.45
    Activations Density 0.001%

    No Known Activations