© 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. 40132
    Prev
    Next
    INDEX
    Explanations

    ACM

    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
     HRM
    -0.74
     ACM
    -0.70
    ACM
    -0.64
    HRM
    -0.63
     Jesuits
    -0.63
     Temperance
    -0.62
    paksa
    -0.61
     Molière
    -0.61
    <bos>
    -0.61
     HCM
    -0.60
    POSITIVE LOGITS
     onOptions
    0.56
    TagHelper
    0.54
     referrerpolicy
    0.53
    AndEndTag
    0.52
    DoubleQuotes
    0.49
    findpost
    0.48
    thra
    0.48
    mær
    0.44
    entery
    0.43
    tably
    0.43
    Activations Density 0.625%

    No Known Activations