© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14103
    Prev
    Next
    INDEX
    Explanations

    variable

    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
    onAttach
    -0.65
    makeConstraints
    -0.61
    TagMode
    -0.60
     EClass
    -0.60
    AnchorTagHelper
    -0.55
    帖最后由
    -0.54
     prenotazione
    -0.52
    TemporalType
    -0.52
     مشين
    -0.51
    transQ
    -0.51
    POSITIVE LOGITS
     pigeons
    0.50
     neceffary
    0.47
     papai
    0.46
     Sonya
    0.46
     Monfieur
    0.46
     Nacho
    0.45
     unſ
    0.44
    
    0.43
     виправивши
    0.43
    ]-->
    0.43
    Activations Density 0.033%

    No Known Activations