© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10
    Prev
    Next
    INDEX
    Explanations

    names of individuals in various contexts

    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
     autorytatywna
    -0.86
    +#+#
    -0.81
    setVerticalGroup
    -0.75
    kusen
    -0.74
     CreateTagHelper
    -0.69
    liament
    -0.68
    aarrggbb
    -0.68
    GEBURTSDATUM
    -0.65
     móvel
    -0.65
    ]$}
    -0.63
    POSITIVE LOGITS
     Jr
    0.63
    ("/:
    0.54
     Perl
    0.52
    '
    0.52
     emeritus
    0.51
    ('/:
    0.48
     ίδ
    0.48
     psycopg
    0.48
     rejoined
    0.47
     petitioner
    0.47
    Activations Density 5.254%

    No Known Activations