© 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. 5-CLT-HP
    4. 2801
    Prev
    Next
    INDEX
    Explanations

    rosy

    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
    dhury
    -0.47
    ayne
    -0.46
    ghted
    -0.45
    handelt
    -0.44
    原始内容存档于
    -0.43
    adillas
    -0.41
     dorados
    -0.40
    श
    -0.40
     Lade
    -0.40
     responsáveis
    -0.40
    POSITIVE LOGITS
    matchCondition
    0.69
    ########.
    0.63
    #
    0.60
    findpost
    0.60
     متعلقه
    0.59
    sidemargin
    0.57
    upol
    0.57
     vitae
    0.54
     moat
    0.54
    (!__
    0.54
    Activations Density 0.001%

    No Known Activations