© 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. 18-RES-MATRYOSHKA-DC
    7. 467
    Prev
    Next
    INDEX
    Explanations

    sentences using the word "I" or "you" in a conditional context or personal narrative

    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.18.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.18.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
     probably
    -0.93
    probably
    -0.92
    Probably
    -0.90
     sicuramente
    -0.83
     Probably
    -0.82
    certainly
    -0.81
     certainly
    -0.77
     prolly
    -0.76
     spesso
    -0.75
     sicherlich
    -0.75
    POSITIVE LOGITS
     reaches
    0.75
     fails
    0.71
     happens
    0.71
     occurs
    0.70
     arrives
    0.69
     becomes
    0.69
    자가
    0.69
     forem
    0.67
     comes
    0.67
     fosse
    0.66
    Activations Density 2.428%

    No Known Activations