© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91217
    Prev
    Next
    INDEX
    Explanations

    year

    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
    CloseOperation
    -0.75
    RefNanny
    -0.57
    vermögen
    -0.51
     AssemblyProduct
    -0.50
    }{*}{}
    -0.49
    protoimpl
    -0.49
    localPosition
    -0.47
    ̀u
    -0.47
    conductors
    -0.47
    subsubsection
    -0.47
    POSITIVE LOGITS
     noDo
    0.61
    canestro
    0.58
    tvguidetime
    0.53
     Protobuf
    0.50
    Abitanti
    0.49
    therly
    0.49
     Efq
    0.48
    ATRE
    0.47
    atzung
    0.47
    etcode
    0.47
    Activations Density 0.009%

    No Known Activations