© 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. 22-RES-MATRYOSHKA-DC
    7. 2694
    Prev
    Next
    INDEX
    Explanations

    the word "or" and verbs describing whether something will successfully continue

    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.22.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.22.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
    elif
    -0.44
     contextLoads
    -0.42
    ेशा
    -0.40
     vero
    -0.37
     höchst
    -0.37
    mia
    -0.35
    ओं
    -0.35
    least
    -0.35
     highly
    -0.35
    Highly
    -0.35
    POSITIVE LOGITS
     without
    2.89
     Without
    2.58
    without
    2.55
    Without
    2.50
     zonder
    2.11
     WITHOUT
    2.09
    WITHOUT
    2.05
     ohne
    2.03
     senza
    1.98
     без
    1.94
    Activations Density 0.355%

    No Known Activations