© 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. 0-CLT-HP
    7. 97427
    Prev
    Next
    INDEX
    Explanations

    code formatting

    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
     perdere
    -0.63
    Naissance
    -0.50
    vyšší
    -0.46
    recyclerview
    -0.41
     Wikimedijinoj
    -0.40
     Zwischen
    -0.40
    FORMAN
    -0.39
    Respuesta
    -0.39
     podla
    -0.39
    inter
    -0.39
    POSITIVE LOGITS
    #
    0.79
     BoxFit
    0.75
    DockStyle
    0.70
    ContentAsync
    0.68
     TextAppearance
    0.67
     &___
    0.65
     setw
    0.63
     MainAxisSize
    0.63
     везе
    0.63
    Browsable
    0.63
    Activations Density 0.113%

    No Known Activations