© 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. 1-CLT-HP
    7. 11855
    Prev
    Next
    INDEX
    Explanations

    radio

    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
    StoryboardSegue
    -0.72
     kasarigan
    -0.57
     dAtA
    -0.56
     propOrder
    -0.50
    pulo
    -0.49
    fortawesome
    -0.45
    ificato
    -0.45
     kohdetta
    -0.42
     متحده
    -0.42
    hasRole
    -0.41
    POSITIVE LOGITS
     المعيارى
    0.65
    ocin
    0.64
    uxxxx
    0.57
    \}\\
    0.57
    zungs
    0.56
    ocer
    0.55
    throw
    0.54
     Throw
    0.54
    InputTagHelper
    0.53
    neath
    0.52
    Activations Density 0.022%

    No Known Activations