© 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. 5781
    Prev
    Next
    INDEX
    Explanations

    Code or documentation

    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
    ImageContext
    -0.73
    sizeCache
    -0.67
    MLLoader
    -0.65
    ########.
    -0.65
    UnsafeEnabled
    -0.65
    GroupLayout
    -0.60
    Jeografia
    -0.59
    yntaxException
    -0.58
    adaptiveStyles
    -0.57
     wireType
    -0.56
    POSITIVE LOGITS
    ypsies
    0.59
    hejiang
    0.58
    glColor
    0.58
     clearColor
    0.54
    isolation
    0.53
    İstinadlar
    0.52
     śmier
    0.51
    ciples
    0.51
    ญิง
    0.50
    Geographie
    0.50
    Activations Density 0.001%

    No Known Activations