© 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. 20138
    Prev
    Next
    INDEX
    Explanations

    the name "John."

    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
    //=
    -0.80
     esimer
    -0.76
     Lakeside
    -0.76
     présidenti
    -0.75
     bây
    -0.75
    setMsg
    -0.70
     artig
    -0.69
    assertSame
    -0.68
     下午
    -0.67
     adecuadas
    -0.67
    POSITIVE LOGITS
     John
    1.30
    John
    1.14
    JOHN
    1.11
     john
    1.09
     JOHN
    1.08
     Deere
    0.99
     Johnnie
    0.98
    john
    0.97
     Johns
    0.97
     Lennon
    0.92
    Activations Density 0.016%

    No Known Activations