© 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. 95026
    Prev
    Next
    INDEX
    Explanations

    Lesser

    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
     useRef
    -0.52
    <bos>
    -0.51
    small
    -0.51
     للمعارف
    -0.50
    BF
    -0.49
    কার
    -0.48
     Tecnología
    -0.48
    flasche
    -0.48
     SMALL
    -0.46
    struzione
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
     Condu
    0.61
    IUrlHelper
    0.59
    CodedInputStream
    0.59
     """
    0.59
    rizona
    0.58
     
    0.58
     المعيارى
    0.58
    veria
    0.58
    DataPropertyName
    0.57
    Activations Density 0.091%

    No Known Activations