© 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. 5-CLT-HP
    7. 2343
    Prev
    Next
    INDEX
    Explanations

    version numbers, ports

    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
     Theſe
    -0.60
     automatiques
    -0.59
    ----</
    -0.56
     supérieurs
    -0.53
     dignité
    -0.53
     précédents
    -0.52
     grå
    -0.52
     stabilité
    -0.52
     réaliste
    -0.51
    parsedMessage
    -0.51
    POSITIVE LOGITS
     having
    0.57
    RepeatedField
    0.57
    исленность
    0.55
     незавершена
    0.54
     []:
    0.52
    ẵn
    0.51
    keye
    0.50
     believing
    0.49
     còn
    0.49
     there
    0.49
    Activations Density 0.004%

    No Known Activations