© 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. 185
    Prev
    Next
    INDEX
    Explanations

    person with interest

    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
    NOPQRST
    -0.55
     AsyncTask
    -0.50
    Autoritní
    -0.50
    IsMutable
    -0.49
     AssemblyCulture
    -0.49
    ="#"><
    -0.47
    Bronnen
    -0.47
    sizeCache
    -0.46
     مشين
    -0.45
    ("$.
    -0.45
    POSITIVE LOGITS
     BorderRadius
    0.64
    onAttach
    0.54
    bootstrapcdn
    0.53
     assolu
    0.52
    otype
    0.51
    Magenta
    0.51
    CardContent
    0.50
     nube
    0.50
    TouchableOpacity
    0.50
    álen
    0.49
    Activations Density 0.001%

    No Known Activations