© 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. 5-CLT-HP
    7. 94370
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     tartalomajánló
    -1.00
    parsedMessage
    -0.79
    彼らの
    -0.79
    Mereka
    -0.79
     Mereka
    -0.76
    ChildScrollView
    -0.75
    adpleegd
    -0.74
    their
    -0.72
     Họ
    -0.72
    they
    -0.71
    POSITIVE LOGITS
     
    0.61
    "
    0.51
    sendRedirect
    0.50
    The
    0.50
    “
    0.46
     &
    0.46
     man
    0.44
     CEO
    0.44
     .
    0.43
     stated
    0.41
    Activations Density 0.001%

    No Known Activations