© 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. 279
    Prev
    Next
    INDEX
    Explanations

    HTML anchor (`<a>`) tags and list items (`<li>`) in a structured format

    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
    transQ
    -0.79
     Roskov
    -0.77
    SOUNDBITE
    -0.69
    ')['
    -0.68
    leroi
    -0.66
    hésite
    -0.66
     âgées
    -0.63
    friger
    -0.61
    ++
    -0.61
     StringTokenizer
    -0.60
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.84
     BoxDecoration
    0.69
    ChildScrollView
    0.69
    endphp
    0.69
    cshtml
    0.65
    InputBorder
    0.64
    jsonwebtoken
    0.64
    ⏟
    0.63
    سوب
    0.63
    </em>
    0.60
    Activations Density 0.543%

    No Known Activations