© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21411
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or identifiers relevant in a technical context

    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
    +#+
    -0.52
    mande
    -0.45
    Hentet
    -0.42
    ram
    -0.41
    aires
    -0.40
     ro
    -0.40
    ';
    -0.40
    jo
    -0.40
    ;
    -0.39
     душ
    -0.39
    POSITIVE LOGITS
    +#+#
    0.91
     متعلقه
    0.77
    IsMutable
    0.77
     itſelf
    0.76
     صوتيه
    0.75
     تانيه
    0.75
     nahilalakip
    0.75
    RTLD
    0.74
    audiovisuel
    0.73
     myſelf
    0.73
    Activations Density 0.002%

    No Known Activations