© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4740
    Prev
    Next
    INDEX
    Explanations

    :

    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
     geogra
    -0.45
    IsContent
    -0.43
     jScrollPane
    -0.43
    Noo
    -0.42
    gai
    -0.42
     alojamiento
    -0.41
     vej
    -0.41
    osto
    -0.40
    PLACEMENT
    -0.39
     localObject
    -0.39
    POSITIVE LOGITS
     Theſe
    0.91
     Efq
    0.82
    NameInMap
    0.75
     uſed
    0.74
     ſtand
    0.74
     purpoſe
    0.72
     anſ
    0.71
    Viited
    0.70
     ſtate
    0.68
     whoſe
    0.68
    Activations Density 0.006%

    No Known Activations