© 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. 20-CLT-HP
    7. 76310
    Prev
    Next
    INDEX
    Explanations

    Responses or acknowledgements

    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
     they
    -1.07
     we
    -1.03
     you
    -0.97
     it
    -0.92
     there
    -0.88
    ]--;
    -0.81
     everyone
    -0.81
     nobody
    -0.78
     someone
    -0.74
     people
    -0.72
    POSITIVE LOGITS
    Check
    0.49
    IVEREF
    0.47
    Note
    0.43
    See
    0.42
    ParallelGroup
    0.42
    IM
    0.41
    Vi
    0.41
    Chat
    0.41
    Get
    0.40
    Pe
    0.40
    Activations Density 0.004%

    No Known Activations