© 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. 2623
    Prev
    Next
    INDEX
    Explanations

    dirt

    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
    ed
    -0.69
    e
    -0.66
    i
    -0.63
    ists
    -0.57
    ities
    -0.56
    ه
    -0.56
    ei
    -0.55
    ist
    -0.54
    otomy
    -0.54
    ی
    -0.54
    POSITIVE LOGITS
     roads
    0.79
    road
    0.79
     road
    0.73
    roads
    0.73
    bag
    0.70
    Road
    0.68
     Roads
    0.65
     Road
    0.64
    Roads
    0.63
    bags
    0.59
    Activations Density 0.002%

    No Known Activations