© 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. 0-CLT-HP
    7. 41234
    Prev
    Next
    INDEX
    Explanations

    combined/combo

    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
     combined
    -0.98
    combined
    -0.71
     total
    -0.58
    Combined
    -0.57
     Combined
    -0.50
     entire
    -0.49
     complex
    -0.48
     complete
    -0.46
     combination
    -0.44
     hold
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.96
    TypedDataSet
    0.92
    +:+
    0.86
    IsMutable
    0.85
     Monfieur
    0.85
    ViewFeatures
    0.84
    parsedMessage
    0.80
    XMLSchema
    0.79
     myſelf
    0.78
    }();
    0.76
    Activations Density 0.025%

    No Known Activations