© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 92763
    Prev
    Next
    INDEX
    Explanations

    also

    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
     }}</
    -0.60
    )}</
    -0.60
    "]="
    -0.59
     récompenses
    -0.59
     }}"></
    -0.59
    ()];
    -0.58
    /*
    -0.57
     Grecs
    -0.56
     }</
    -0.56
     travailleurs
    -0.56
    POSITIVE LOGITS
    errHandler
    0.54
    :
    0.52
     setPrice
    0.52
     parabolic
    0.49
     henvisninger
    0.49
    ...
    0.48
     tangent
    0.48
    oretical
    0.48
    JpaRepository
    0.47
     governor
    0.47
    Activations Density 0.010%

    No Known Activations