© 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. 4-CLT-HP
    7. 975
    Prev
    Next
    INDEX
    Explanations

    a

    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
     quieras
    -0.58
    num
    -0.56
    numbers
    -0.53
     antaranya
    -0.52
     quiera
    -0.52
     numbers
    -0.50
     CanadaChoose
    -0.49
    CWE
    -0.49
     autorytatywna
    -0.48
     darunter
    -0.48
    POSITIVE LOGITS
    LElement
    0.60
    Captor
    0.59
    ]='\
    0.59
    躇
    0.56
     OrderedDict
    0.56
     TextEditing
    0.55
    ExecuteReader
    0.55
    AutoField
    0.55
     Frontera
    0.54
     aquarium
    0.53
    Activations Density 0.003%

    No Known Activations