© 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. 94185
    Prev
    Next
    INDEX
    Explanations

    cited

    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
     the
    -0.92
    GEBURTSDATUM
    -0.76
     how
    -0.67
    Autoritní
    -0.66
    évaluateur
    -0.66
     otomatig
    -0.66
    WithIOException
    -0.65
     jScrollPane
    -0.65
    arraycopy
    -0.64
    Diweddarwch
    -0.64
    POSITIVE LOGITS
     Woodford
    0.52
    styleType
    0.51
    zzar
    0.47
    head
    0.47
    Trem
    0.47
    MOS
    0.46
    ätie
    0.46
    Anyone
    0.46
    หวัด
    0.45
    handsome
    0.45
    Activations Density 0.001%

    No Known Activations