© 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. 0-CLT-HP
    7. 94669
    Prev
    Next
    INDEX
    Explanations

    teams and relationships

    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
    存于互联网档案馆
    -0.95
     teammates
    -0.95
    KURZBESCHREIBUNG
    -0.94
     classmates
    -0.92
     Efq
    -0.89
     peers
    -0.87
     neighbours
    -0.86
     mergeFrom
    -0.83
     purpoſe
    -0.82
    AddTagHelper
    -0.82
    POSITIVE LOGITS
     in
    0.40
     at
    0.39
     we
    0.38
    ommen
    0.38
    hips
    0.38
     denken
    0.37
     existir
    0.37
     mempel
    0.37
    writeInt
    0.37
     are
    0.36
    Activations Density 0.083%

    No Known Activations