© 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. 97348
    Prev
    Next
    INDEX
    Explanations

    science, technology, nanotubes

    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
     الحره
    -0.65
    ModelAdmin
    -0.63
     sketching
    -0.59
    __':
    -0.58
    hoodie
    -0.55
     unt
    -0.55
     sketch
    -0.55
     asl
    -0.55
     חיצוניים
    -0.54
     Minden
    -0.54
    POSITIVE LOGITS
    oredCriteria
    0.58
    vivencia
    0.56
     pecho
    0.53
     écou
    0.52
    ugno
    0.51
    viens
    0.51
     merve
    0.51
     elettron
    0.50
     économies
    0.49
    cro
    0.47
    Activations Density 0.030%

    No Known Activations