© 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. 42144
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     two
    -1.22
     deux
    -1.13
     three
    -1.07
    two
    -0.98
     four
    -0.98
     trois
    -0.96
    Two
    -0.94
     Two
    -0.93
    <eos>
    -0.91
     três
    -0.90
    POSITIVE LOGITS
     myſelf
    1.50
     Efq
    1.43
     Jefus
    1.30
     itſelf
    1.25
     Monfieur
    1.22
     themſelves
    1.21
     Majefty
    1.21
     ſche
    1.20
     pleaſure
    1.20
     leaſt
    1.16
    Activations Density 0.292%

    No Known Activations