© 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. 40185
    Prev
    Next
    INDEX
    Explanations

    gear

    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
     factor
    -1.08
     tour
    -1.01
     gear
    -0.96
    factor
    -0.96
     Factor
    -0.93
     Tour
    -0.87
    FACTOR
    -0.83
    Factor
    -0.82
    tour
    -0.82
     pace
    -0.81
    POSITIVE LOGITS
    ability
    0.60
    ings
    0.58
    able
    0.57
    ed
    0.54
    set
    0.54
    ups
    0.53
    httphttps
    0.52
    μμ
    0.52
    ign
    0.52
    bo
    0.52
    Activations Density 0.129%

    No Known Activations