© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    Process

    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
     ProtoMessage
    -0.51
    TargetException
    -0.50
     makeStyles
    -0.50
     Bioaccumulative
    -0.48
    bufio
    -0.48
    featureID
    -0.47
    TagMode
    -0.46
    Fordítás
    -0.45
    UnusedPrivate
    -0.45
     GenerationType
    -0.45
    POSITIVE LOGITS
     تانيه
    0.58
     just
    0.52
     ujednoznacz
    0.51
    $_.
    0.50
     متعلقه
    0.48
     المعرف
    0.48
     hjäl
    0.48
     Just
    0.48
     chemin
    0.48
    just
    0.47
    Activations Density 0.001%

    No Known Activations