© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1654
    Prev
    Next
    INDEX
    Explanations

    the word "is" preceded by other words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.69
     linkovi
    -0.66
    Personensuche
    -0.64
    trophic
    -0.63
     Himo
    -0.61
    AnimationsModule
    -0.60
    diffuse
    -0.60
     يتيمه
    -0.60
     <=",
    -0.60
    ]<<
    -0.59
    POSITIVE LOGITS
     dieux
    0.54
    ásban
    0.54
     ivelany
    0.52
     :
    0.52
    的是
    0.51
    fflush
    0.50
    äinen
    0.50
    Clik
    0.49
    今度は
    0.49
    RegistryLite
    0.48
    Activations Density 0.904%

    No Known Activations