© 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. 41292
    Prev
    Next
    INDEX
    Explanations

    increased

    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
    .
    -0.49
     in
    -0.44
     each
    -0.44
     for
    -0.42
    '
    -0.39
    :
    -0.39
     when
    -0.38
     so
    -0.38
     about
    -0.37
     over
    -0.37
    POSITIVE LOGITS
     Normdatei
    1.05
     كومونز
    1.03
     صوتيه
    1.03
     myſelf
    1.03
     Савезне
    0.99
    TagMode
    0.98
     otomatig
    0.98
     iſt
    0.97
    ^(@)
    0.96
    Geplaatst
    0.96
    Activations Density 0.198%

    No Known Activations