© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93829
    Prev
    Next
    INDEX
    Explanations

    time

    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
    къ
    -0.47
    ʃ
    -0.47
     of
    -0.46
     klokken
    -0.46
    qtype
    -0.44
    IBAction
    -0.44
     noticing
    -0.43
    LSTM
    -0.42
    kloped
    -0.42
     to
    -0.42
    POSITIVE LOGITS
     that
    0.79
     OFDb
    0.72
     since
    0.71
     in
    0.70
    since
    0.62
    SourceChecksum
    0.59
     للاسماء
    0.58
    ättern
    0.58
    OGND
    0.57
     Since
    0.56
    Activations Density 0.001%

    No Known Activations