© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43342
    Prev
    Next
    INDEX
    Explanations

    filler words

    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
     so
    -2.33
    so
    -1.63
     så
    -1.25
     So
    -1.10
    So
    -1.05
     так
    -1.05
     così
    -0.98
     
    -0.93
    如此
    -0.82
     (
    -0.82
    POSITIVE LOGITS
     Monfieur
    1.44
     itſelf
    1.41
     myſelf
    1.41
     pleaſure
    1.39
     Efq
    1.32
     Majefty
    1.31
     ſtate
    1.28
     houſe
    1.27
     purpoſe
    1.25
     Eſ
    1.24
    Activations Density 0.331%

    No Known Activations