© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 524
    Prev
    Next
    INDEX
    Explanations

    testimonies related to specific incidents or forensic evidence

    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
    QFont
    -0.45
    CascadeType
    -0.43
    Executors
    -0.43
    RUNTIME
    -0.42
    helves
    -0.42
    printStackTrace
    -0.42
     platforms
    -0.42
    }),
    -0.41
    <bos>
    -0.41
    ensure
    -0.40
    POSITIVE LOGITS
     виправивши
    0.99
    parsedMessage
    0.91
     Possibly
    0.85
    somewhere
    0.83
     possibly
    0.82
     somewhere
    0.82
    EDEFAULT
    0.81
    Somewhere
    0.81
    possibly
    0.80
     Somewhere
    0.80
    Activations Density 2.496%

    No Known Activations