© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97520
    Prev
    Next
    INDEX
    Explanations

    attendant

    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
     "..\..\
    -0.57
    
    -0.56
    PreferredItem
    -0.55
     متعلقه
    -0.52
     "..\..\..\
    -0.50
    diep
    -0.49
    ഴ
    -0.47
    PERATURE
    -0.47
    kip
    -0.45
     merito
    -0.45
    POSITIVE LOGITS
    henswürdigkeiten
    0.63
    Personendaten
    0.63
    Enllaces
    0.61
     continúas
    0.57
     виправивши
    0.54
     Audiodateien
    0.50
    Transcription
    0.49
    PRWEB
    0.48
     Gazetteer
    0.47
    下载附件
    0.47
    Activations Density 0.001%

    No Known Activations