© 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. 4615
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    UrlResolution
    -0.60
    HostException
    -0.57
     uintptr
    -0.57
    queryInterface
    -0.53
    ToAction
    -0.53
    ClientSize
    -0.52
    OrNil
    -0.52
    TokenNameLBRACE
    -0.49
    znál
    -0.48
    Initializable
    -0.48
    POSITIVE LOGITS
     الرياضيه
    0.59
     المعيارى
    0.59
     Wissenschaften
    0.54
     pinulongan
    0.53
    __':
    0.53
    нциклопе
    0.52
    UnusedPrivate
    0.50
     Normdatei
    0.50
     Trace
    0.50
    ilet
    0.48
    Activations Density 0.005%

    No Known Activations