© 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. 94146
    Prev
    Next
    INDEX
    Explanations

    Technical documentation excerpts

    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
     of
    -0.68
    InputBorder
    -0.55
     in
    -0.54
    älv
    -0.51
    rawDesc
    -0.49
     base
    -0.48
    ChildScrollView
    -0.47
     at
    -0.47
    amur
    -0.47
    of
    -0.46
    POSITIVE LOGITS
     propOrder
    0.63
     betweenstory
    0.61
    pausal
    0.61
    CPtr
    0.58
     gawas
    0.57
     disambiguazione
    0.56
     correctes
    0.56
     Theses
    0.56
     semelh
    0.55
    szy
    0.55
    Activations Density 0.003%

    No Known Activations