© 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. 479
    Prev
    Next
    INDEX
    Explanations

    capitalized words, book titles, and newspaper titles appearing near dates

    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
     houſe
    -1.01
     purpoſe
    -1.01
     raiſ
    -0.93
     myſelf
    -0.92
     ſtate
    -0.91
     ſta
    -0.91
     uſed
    -0.91
     reaſon
    -0.90
     emeritus
    -0.90
     pleaſure
    -0.89
    POSITIVE LOGITS
     jambes
    0.65
     Including
    0.63
     boî
    0.61
     That
    0.60
     Using
    0.60
     bénéfices
    0.57
     Which
    0.56
     preuves
    0.56
     väg
    0.55
     têtes
    0.55
    Activations Density 2.044%

    No Known Activations