© 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. 97452
    Prev
    Next
    INDEX
    Explanations

    objects

    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
     myſelf
    -1.51
     feroit
    -1.50
     auroit
    -1.48
     pouvoit
    -1.48
     ainfi
    -1.46
     avoient
    -1.43
     étoit
    -1.42
     Houſe
    -1.40
     mauva
    -1.37
     plufieurs
    -1.37
    POSITIVE LOGITS
    s
    0.77
     in
    0.73
     
    0.72
    .
    0.68
     (
    0.65
     pas
    0.63
    ,
    0.63
     and
    0.60
     the
    0.60
     so
    0.60
    Activations Density 0.673%

    No Known Activations