© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4061
    Prev
    Next
    INDEX
    Explanations

    forum answers

    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
    sidemargin
    -0.55
    DockStyle
    -0.53
     eminence
    -0.52
     stratigraphy
    -0.49
     Infórmanos
    -0.47
     voca
    -0.47
    BASEPATH
    -0.47
     whiteness
    -0.47
     Clough
    -0.46
     exclusively
    -0.46
    POSITIVE LOGITS
    RegressionTest
    0.75
     and
    0.72
     <<<<<<<<<<<<<<
    0.60
    sprechend
    0.59
    таратура
    0.56
    wapV
    0.54
    UrlResolution
    0.52
    +:+
    0.52
    JvmStatic
    0.52
     to
    0.51
    Activations Density 0.006%

    No Known Activations