© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40410
    Prev
    Next
    INDEX
    Explanations

    en dash

    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
     –
    -1.84
     —
    -1.48
     --
    -1.46
     -
    -1.36
    ,
    -1.20
    —
    -1.11
     −
    -1.05
     ―
    -0.82
    :
    -0.81
    --
    -0.79
    POSITIVE LOGITS
     ainfi
    1.03
     sauvages
    0.97
     quelcon
    0.94
     définiti
    0.93
     normaux
    0.92
     becauſe
    0.89
     auroit
    0.89
     avoient
    0.89
     feroit
    0.89
     plufieurs
    0.88
    Activations Density 0.243%

    No Known Activations