© 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. 34
    Prev
    Next
    INDEX
    Explanations

    error codes or error messages related to system calls

    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
    ьаж
    -1.36
     Италијани
    -1.30
    oredCriteria
    -1.27
    RegressionTest
    -1.23
     betweenstory
    -1.16
    Vidite
    -1.15
     '\\;'
    -1.15
    WithIOException
    -1.14
    AsUp
    -1.13
    ArrowToggle
    -1.08
    POSITIVE LOGITS
    \{\\
    0.78
    󠁢
    0.59
    __(/*!
    0.55
    enumi
    0.54
    fortawesome
    0.51
     
    0.49
     تانيه
    0.45
    </thead>
    0.45
    [toxicity=0]
    0.45
     also
    0.43
    Activations Density 18.589%

    No Known Activations