© 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. 5-CLT-HP
    7. 3079
    Prev
    Next
    INDEX
    Explanations

    media, socialization

    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
    tagHelperRunner
    -0.62
     craindre
    -0.57
     réguli
    -0.52
     publiques
    -0.51
     Efq
    -0.48
     croire
    -0.48
     commerciaux
    -0.47
    rupal
    -0.47
     oublier
    -0.47
     castelo
    -0.46
    POSITIVE LOGITS
    Agents
    0.67
    новниш
    0.66
     agents
    0.60
     فريبيس
    0.59
    الحياه
    0.58
     protoimpl
    0.57
     FetchType
    0.56
    oa̍t
    0.55
    agents
    0.55
     Agents
    0.54
    Activations Density 0.001%

    No Known Activations