© 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. 57
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurement and analysis

    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
    antMatchers
    -0.61
    /
    -0.60
    ...
    -0.59
     
    -0.52
    brück
    -0.50
    </em>
    -0.49
    XMLSchema
    -0.48
    chan
    -0.48
     Great
    -0.48
     gran
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.91
     ſche
    0.83
     snippetHide
    0.82
     <<<<<<<<<<<<<<
    0.80
    脚注の使い方
    0.79
     nahilalakip
    0.79
    Tikang
    0.79
     ſtate
    0.77
     Eſ
    0.77
     tartalomajánló
    0.75
    Activations Density 5.039%

    No Known Activations