© 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. 4538
    Prev
    Next
    INDEX
    Explanations

    alternatives or comparisons

    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
    WebControls
    -0.74
    writeField
    -0.66
     she
    -0.62
    she
    -0.60
    Rujuakan
    -0.59
    RectangleBorder
    -0.57
    JoinTable
    -0.57
    spender
    -0.56
    EndInit
    -0.55
     månader
    -0.55
    POSITIVE LOGITS
     reflecting
    0.52
     blending
    0.50
     rejecting
    0.49
     bothering
    0.49
     denying
    0.48
     reducing
    0.47
     releasing
    0.47
     focusing
    0.46
     integrating
    0.46
     hitting
    0.45
    Activations Density 0.001%

    No Known Activations