© 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. 93161
    Prev
    Next
    INDEX
    Explanations

    how

    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
    SequentialGroup
    -0.55
    tvguidetime
    -0.46
    them
    -0.45
    嘩
    -0.43
     tipped
    -0.43
    :].
    -0.42
    tipped
    -0.41
    <?
    -0.41
    [](
    -0.41
     AppBundle
    -0.41
    POSITIVE LOGITS
     can
    0.92
     do
    0.81
     might
    0.78
     does
    0.76
     Can
    0.73
     Might
    0.72
     should
    0.71
     Do
    0.71
     Does
    0.67
     Should
    0.65
    Activations Density 0.002%

    No Known Activations