© 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. 5669
    Prev
    Next
    INDEX
    Explanations

    terms related to actions or processes involved in data processing and improvement

    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
     NSCoder
    -0.65
    bootstrapcdn
    -0.60
    MLLoader
    -0.59
     Normdatei
    -0.58
     gouvernements
    -0.56
    -------------</
    -0.54
    AxisAlignment
    -0.54
    createFrom
    -0.54
     með
    -0.53
     الحره
    -0.52
    POSITIVE LOGITS
    脚注の使い方
    0.91
     <<<<<<<<<<<<<<
    0.64
    \{\\
    0.62
    __":
    0.61
     okuyayım
    0.59
    enumi
    0.58
    Рис
    0.58
     jsonify
    0.57
    CGRectMake
    0.57
    __':
    0.56
    Activations Density 0.504%

    No Known Activations