© 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. 1-CLT-HP
    7. 14406
    Prev
    Next
    INDEX
    Explanations

    schools

    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
    ագրություններ
    -0.70
    Tembelea
    -0.70
    CloseOperation
    -0.69
     Wiktionnaire
    -0.63
     trå
    -0.62
    radura
    -0.58
    featureID
    -0.58
     gynhyrchwyd
    -0.57
    EFIAPI
    -0.57
     الرياضيه
    -0.57
    POSITIVE LOGITS
     Paglinawan
    0.53
    lccn
    0.46
     Spri
    0.45
    Progressive
    0.45
     Egli
    0.44
     Progressive
    0.43
     clean
    0.42
     circula
    0.42
     probate
    0.42
     NPA
    0.41
    Activations Density 0.007%

    No Known Activations