© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16574
    Prev
    Next
    INDEX
    Explanations

    programming code snippets or references

    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
    Vidite
    -0.71
    pastebin
    -0.60
     Affidavit
    -0.60
     '\\;'
    -0.58
     JNI
    -0.57
    CloseOperation
    -0.57
     Paroles
    -0.56
    Initialization
    -0.56
    loft
    -0.56
    Loft
    -0.56
    POSITIVE LOGITS
     للاسماء
    0.66
    complexType
    0.59
     createState
    0.57
    endpush
    0.57
    istoitu
    0.57
    wieś
    0.56
    Smarty
    0.53
    gın
    0.52
    arker
    0.52
     createContext
    0.51
    Activations Density 0.042%

    No Known Activations