© 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. 4775
    Prev
    Next
    INDEX
    Explanations

    coding

    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
    ISupport
    -0.75
     متعلقه
    -0.63
     négociations
    -0.58
    insee
    -0.57
     []).
    -0.57
    SequentialGroup
    -0.55
    Boden
    -0.54
     whiteColor
    -0.54
    #+#
    -0.53
    copg
    -0.52
    POSITIVE LOGITS
    JspWriter
    0.63
    Дереккөздер
    0.54
    liesslich
    0.52
     that
    0.52
    KURZBESCHREIBUNG
    0.50
     ExecuteAsync
    0.49
    Glej
    0.48
     vPvB
    0.48
     kinds
    0.47
     otomatig
    0.47
    Activations Density 0.001%

    No Known Activations