© 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. 10808
    Prev
    Next
    INDEX
    Explanations

    letters and alphanumeric representations in a structured format

    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
     umani
    -0.59
     GenerationType
    -0.58
    úgó
    -0.58
     soggior
    -0.57
    argout
    -0.57
    MemoryWarning
    -0.56
    WebServlet
    -0.55
    WebKit
    -0.54
    HKEY
    -0.53
    CastException
    -0.53
    POSITIVE LOGITS
    ió
    0.55
    "):
    0.55
    évaluateur
    0.54
    "}>
    0.54
     plafon
    0.53
    いろいろ
    0.50
    .)}
    0.50
    NewUrlParser
    0.49
    ς
    0.49
    силання
    0.49
    Activations Density 0.142%

    No Known Activations