© 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. 2549
    Prev
    Next
    INDEX
    Explanations

    Quality

    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
    المناصب
    -0.66
     insuffisamment
    -0.61
    =$?
    -0.60
    مصادر
    -0.59
     Edges
    -0.58
    Edges
    -0.58
    piac
    -0.57
     depositphotos
    -0.56
     Levinson
    -0.56
    EDGE
    -0.56
    POSITIVE LOGITS
    ]")]
    0.42
    forChild
    0.42
     stream
    0.40
     Stream
    0.39
    forRoot
    0.39
    ResponseWriter
    0.38
    fclose
    0.38
     tami
    0.37
     resc
    0.37
     tử
    0.36
    Activations Density 0.000%

    No Known Activations