© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40938
    Prev
    Next
    INDEX
    Explanations

    Sug

    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
    oneofs
    -0.95
    abestanden
    -0.90
    findpost
    -0.89
     cloud
    -0.84
     Administrativna
    -0.84
     clean
    -0.83
     Signalez
    -0.82
     Cleanup
    -0.81
     مرئيه
    -0.81
     cleanest
    -0.80
    POSITIVE LOGITS
    ring
    0.71
    ness
    0.63
    ship
    0.62
    less
    0.61
    s
    0.60
    ning
    0.56
    table
    0.52
    spec
    0.52
    r
    0.52
    i
    0.52
    Activations Density 1.639%

    No Known Activations