© 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. 12-RES-MATRYOSHKA-DC
    7. 14073
    Prev
    Next
    INDEX
    Explanations

    repeated references to "the."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     The
    -0.64
    The
    -0.60
     the
    -0.56
     He
    -0.55
    u
    -0.54
     We
    -0.54
    <b>
    -0.50
    <eos>
    -0.50
     
    -0.50
     La
    -0.47
    POSITIVE LOGITS
    NUMX
    1.12
     itſelf
    1.07
     leſs
    1.03
     myſelf
    1.02
     BoxFit
    1.01
    ^(@)
    1.01
     useRouter
    0.97
     purpoſe
    0.97
     $_(
    0.94
     faſt
    0.93
    Activations Density 0.043%

    No Known Activations