© 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. 20-CLT-HP
    7. 71971
    Prev
    Next
    INDEX
    Explanations

    helping/doing

    np_max-act-logits · 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
     transfieras
    -0.95
    +#+#
    -0.82
     nakalista
    -0.80
    migrationBuilder
    -0.79
    ftagPool
    -0.79
     defaultstate
    -0.78
     chi̍t
    -0.77
     '\\;'
    -0.77
    رشف
    -0.75
     BoxFit
    -0.72
    POSITIVE LOGITS
     hard
    0.62
     working
    0.60
     read
    0.49
     ris
    0.43
     cooking
    0.43
     surla
    0.40
     bea
    0.38
     blo
    0.38
     ngh
    0.38
    Atta
    0.36
    Activations Density 0.001%

    No Known Activations