© 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. 0-CLT-HP
    7. 42438
    Prev
    Next
    INDEX
    Explanations

    shed

    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
    finally
    -1.08
     sheds
    -1.07
     finally
    -1.03
     shed
    -1.03
     finalmente
    -1.01
    reszcie
    -0.96
    NameInMap
    -0.93
     suddenly
    -0.93
     наконец
    -0.88
    suddenly
    -0.88
    POSITIVE LOGITS
     general
    0.56
     entire
    0.56
     complete
    0.54
     total
    0.51
     choice
    0.51
     Bu
    0.50
     opinion
    0.50
     lo
    0.50
     direct
    0.50
    ses
    0.49
    Activations Density 0.567%

    No Known Activations