© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4893
    Prev
    Next
    INDEX
    Explanations

    code

    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
    存于互联网档案馆
    -0.78
    原始内容存档于
    -0.77
     ModelExpression
    -0.75
     Préférences
    -0.68
     يتيمه
    -0.68
    Sucesor
    -0.67
     comuniques
    -0.66
    Datuak
    -0.65
    "});
    -0.63
    CppMethod
    -0.63
    POSITIVE LOGITS
    RunAsync
    0.56
     finally
    0.50
     simultaneously
    0.49
     ſeveral
    0.48
     others
    0.47
     ſte
    0.45
     the
    0.44
     following
    0.44
     now
    0.44
     leaſt
    0.44
    Activations Density 0.174%

    No Known Activations