© 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. 4-CLT-HP
    7. 645
    Prev
    Next
    INDEX
    Explanations

    origins, movement, processes

    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
    acak
    -0.40
    כשיו
    -0.40
    setError
    -0.40
    вата
    -0.38
    在了
    -0.38
    DAT
    -0.38
    Ys
    -0.38
    enna
    -0.37
     cenar
    -0.37
     inve
    -0.36
    POSITIVE LOGITS
    +#+#
    0.84
    SequentialGroup
    0.83
    ########.
    0.77
    addContainerGap
    0.75
     للاسماء
    0.72
     estekak
    0.72
    webElementXpaths
    0.71
    DOCTYPE
    0.68
    InjectAttribute
    0.66
    DockStyle
    0.66
    Activations Density 0.005%

    No Known Activations