© 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. 24-RES-MATRYOSHKA-DC
    7. 610
    Prev
    Next
    INDEX
    Explanations

    French-language text including the verb "vas."

    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/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arrête
    -0.58
     quantization
    -0.56
    améli
    -0.56
     riusc
    -0.54
     незавершена
    -0.53
     Frü
    -0.52
     regresó
    -0.51
     rispond
    -0.50
    texttt
    -0.50
    saat
    -0.49
    POSITIVE LOGITS
     INTERESAR
    0.56
     defender
    0.54
     getting
    0.54
     re
    0.53
     being
    0.52
    EndContext
    0.52
     oprot
    0.52
     LoggerFactory
    0.49
    rometer
    0.49
     having
    0.48
    Activations Density 0.125%

    No Known Activations