© 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. 280
    Prev
    Next
    INDEX
    Explanations

    proper names; specifically, last names, and sometimes first and last names

    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
    ,
    -0.56
     most
    -0.52
    -
    -0.51
    .
    -0.50
     two
    -0.50
     some
    -0.49
     the
    -0.49
     a
    -0.49
     &
    -0.48
     were
    -0.48
    POSITIVE LOGITS
     تضيفلها
    1.10
    OGND
    0.99
    Hentet
    0.98
    ########.
    0.94
    tagHelperRunner
    0.92
    Personensuche
    0.90
    الدراسه
    0.85
    :✨
    0.84
     متعلقه
    0.82
    parsedMessage
    0.82
    Activations Density 1.931%

    No Known Activations