© 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. 40730
    Prev
    Next
    INDEX
    Explanations

    conversational filler

    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
    SourceChecksum
    -1.16
    Datuak
    -1.06
    InjectAttribute
    -1.05
     дописавши
    -1.05
    SharedCtor
    -1.03
     Савезне
    -1.02
     propOrder
    -1.01
    GEBURTSDATUM
    -1.01
     صوتيه
    -1.00
    setVerticalGroup
    -0.99
    POSITIVE LOGITS
     cio
    0.41
     decou
    0.41
    ,
    0.41
    Co
    0.39
    所
    0.38
     as
    0.37
    ();
    0.36
    二
    0.36
    ecas
    0.35
     spol
    0.35
    Activations Density 0.423%

    No Known Activations