© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46138
    Prev
    Next
    INDEX
    Explanations

    also

    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
     also
    -0.61
    ,
    -0.52
     and
    -0.52
    <eos>
    -0.49
     ar
    -0.47
     (
    -0.46
     can
    -0.45
    ()][
    -0.43
     ever
    -0.43
     Also
    -0.43
    POSITIVE LOGITS
     houſe
    0.91
     Theſe
    0.87
     ſtate
    0.85
    IntoConstraints
    0.85
     Efq
    0.84
     Perſ
    0.84
     pleaſure
    0.83
     Monfieur
    0.83
     whoſe
    0.78
     purpoſe
    0.77
    Activations Density 0.219%

    No Known Activations