© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24950
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases, particularly those that begin with "Did you."

    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
    Negative Logits
     שוליים
    -0.96
    SharedDtor
    -0.95
     Audiodateien
    -0.92
    دانشنامهٔ
    -0.91
    ReusableCell
    -0.90
    laterra
    -0.85
    MigrationBuilder
    -0.84
    ])*
    -0.83
    \}}
    -0.81
    ⓧ
    -0.81
    POSITIVE LOGITS
    DID
    0.87
     DID
    0.73
    pyplot
    0.67
    einander
    0.67
    did
    0.66
    pośred
    0.66
     Esco
    0.65
     Didi
    0.63
    gil
    0.62
     étape
    0.58
    Activations Density 0.047%

    No Known Activations