© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45504
    Prev
    Next
    INDEX
    Explanations

    hosting, translation, filtration

    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
    ArgsConstructor
    -0.94
    AndEndTag
    -0.93
     Efq
    -0.92
     Hosted
    -0.90
     iſt
    -0.85
     greateſt
    -0.84
    Personendaten
    -0.83
     itſelf
    -0.82
     myſelf
    -0.82
     wireType
    -0.82
    POSITIVE LOGITS
     
    0.64
     By
    0.57
     Ver
    0.55
     ver
    0.54
     by
    0.53
     Ma
    0.52
     the
    0.51
     i
    0.50
     Has
    0.49
     U
    0.48
    Activations Density 0.096%

    No Known Activations