© 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. 0-CLT-HP
    7. 93253
    Prev
    Next
    INDEX
    Explanations

    magnitude

    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
     
    -0.67
     t
    -0.67
     "
    -0.67
     '
    -0.65
     “
    -0.65
     un
    -0.65
    -
    -0.65
     all
    -0.65
     sub
    -0.65
     T
    -0.64
    POSITIVE LOGITS
     becauſe
    1.32
     >=",
    1.23
    expandindo
    1.17
     myſelf
    1.17
    IsContent
    1.16
     Theſe
    1.15
    ^(@)
    1.13
     Мексичка
    1.12
     ſeveral
    1.12
     whoſe
    1.11
    Activations Density 0.012%

    No Known Activations