© 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. 19137
    Prev
    Next
    INDEX
    Explanations

    specific structural indicators, such as dashes or arrows indicating sections or transitions in text

    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
     εν
    -0.54
    
    -0.54
    stdafx
    -0.52
    PrototypeOf
    -0.52
     Boas
    -0.51
    TagHelper
    -0.51
     kabupaten
    -0.50
    argout
    -0.50
    cstdlib
    -0.49
     MonoBehaviour
    -0.48
    POSITIVE LOGITS
     propOrder
    0.71
    InjectAttribute
    0.63
     emphat
    0.61
    mybatisplus
    0.59
     تانيه
    0.58
    ніципалі
    0.56
    Билгалдахарш
    0.56
     Mercure
    0.56
    uxxxx
    0.55
     ***!
    0.54
    Activations Density 0.001%

    No Known Activations