© 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. 4-CLT-HP
    7. 3052
    Prev
    Next
    INDEX
    Explanations

    Caleb

    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
    StructEnd
    -0.71
    UnusedPrivate
    -0.70
     protoimpl
    -0.70
     himo
    -0.67
    AddTagHelper
    -0.65
     мәкал
    -0.62
     Taktlose
    -0.61
     Réponses
    -0.61
    ंदीखरीदारी
    -0.59
     كومونز
    -0.58
    POSITIVE LOGITS
    Trama
    0.63
    ariste
    0.48
    이는
    0.47
    merk
    0.46
    licability
    0.46
    ější
    0.46
    Filmographie
    0.46
    illah
    0.45
    ppig
    0.45
    ervation
    0.45
    Activations Density 0.001%

    No Known Activations