© 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. 97135
    Prev
    Next
    INDEX
    Explanations

    he

    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
     eventuali
    -0.52
    󠁿
    -0.52
     chré
    -0.47
    sterious
    -0.46
     lặng
    -0.45
    gean
    -0.45
    //
    -0.45
    انجليز
    -0.45
     longest
    -0.44
    }}+\
    -0.44
    POSITIVE LOGITS
     ever
    0.63
    EndTag
    0.63
    StructEnd
    0.59
    SequentialGroup
    0.57
    ModelBuilder
    0.56
    TestingModule
    0.56
    ParallelGroup
    0.55
    Portale
    0.55
    detectChanges
    0.54
     Мексичка
    0.53
    Activations Density 0.003%

    No Known Activations