© 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. 2663
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ed' that are descriptors or past tense verbs

    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
     nulle
    -0.46
     maleta
    -0.45
     financières
    -0.44
     veneta
    -0.44
    are
    -0.43
     historiques
    -0.43
     extrêmement
    -0.42
     Schild
    -0.42
    j
    -0.41
    paan
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.88
     initComponents
    0.84
     विश्वसनीयता
    0.84
    yntaxException
    0.81
     Paglinawan
    0.76
    ONSORED
    0.75
    RenderAtEndOf
    0.73
    aughter
    0.71
    plained
    0.71
    Personensuche
    0.69
    Activations Density 0.391%

    No Known Activations