© 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. 96346
    Prev
    Next
    INDEX
    Explanations

    simultaneously

    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
    ſelf
    -0.69
     Houſe
    -0.68
    ſelves
    -0.65
     stället
    -0.65
     themſelves
    -0.63
     perfons
    -0.62
     behulp
    -0.61
    ományos
    -0.61
     verksamhet
    -0.60
     allmän
    -0.59
    POSITIVE LOGITS
    fjspx
    0.65
    __*/
    0.56
    nonatomic
    0.56
    artifactId
    0.55
     ProtoMessage
    0.54
    ValueStyle
    0.53
    rawDesc
    0.52
    HtmlAttribute
    0.52
     des
    0.51
    PrototypeOf
    0.50
    Activations Density 0.004%

    No Known Activations