© 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. 16729
    Prev
    Next
    INDEX
    Explanations

    numerical values and brackets

    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
     Hoch
    -0.68
    ([
    -0.59
     McLaughlin
    -0.56
     ön
    -0.54
    Titus
    -0.54
    -\
    -0.54
     المعيارى
    -0.54
    laşı
    -0.53
    ocio
    -0.53
    oslav
    -0.53
    POSITIVE LOGITS
    djangoproject
    1.04
     Houſe
    1.00
    ſelf
    0.96
     Shakspeare
    0.92
     ―――――
    0.91
     Efq
    0.90
     ་་
    0.86
     houſe
    0.85
    tableFuture
    0.84
    NUMX
    0.83
    Activations Density 0.020%

    No Known Activations