© 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. 720
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "if."

    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
    they
    -0.68
    让我们
    -0.59
    讓我們
    -0.54
    THEY
    -0.50
    We
    -0.49
     chúng
    -0.49
    we
    -0.48
    私も
    -0.48
    UpInside
    -0.48
    给我们
    -0.48
    POSITIVE LOGITS
     you
    3.28
     você
    1.74
    you
    1.73
     vous
    1.63
     شما
    1.36
     вам
    1.35
     вами
    1.34
     вас
    1.33
    You
    1.30
     usted
    1.28
    Activations Density 1.339%

    No Known Activations