© 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. 19649
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing disbelief or questioning statements

    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
    MigrationBuilder
    -0.66
    twimg
    -0.62
    ScopeManager
    -0.57
    ViewFeatures
    -0.54
     Exacts
    -0.49
    reau
    -0.45
    insen
    -0.45
    Personen
    -0.44
    flü
    -0.44
    providedIn
    -0.43
    POSITIVE LOGITS
    endphp
    0.69
    adget
    0.66
     Савезне
    0.64
    enderror
    0.61
     חיצוניים
    0.59
    >*/
    0.58
    ]),
    0.56
    onAttach
    0.56
    };*/
    0.56
    ''')
    0.54
    Activations Density 0.045%

    No Known Activations