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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26086
    Prev
    Next
    INDEX
    Explanations

    contexts involving location or situations described with "where."

    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
    +#+#
    -0.87
    MigrationBuilder
    -0.85
    mybatisplus
    -0.84
    ]")]
    -0.78
    sizeCache
    -0.76
    principalTable
    -0.75
    invokeLater
    -0.74
     ExecuteAsync
    -0.74
     HasFactory
    -0.71
    XtraGrid
    -0.70
    POSITIVE LOGITS
    createUser
    0.53
    ROR
    0.51
    babkan
    0.51
     bedienen
    0.50
    mare
    0.50
    Cos
    0.49
    raš
    0.49
     Cos
    0.49
    rali
    0.48
    ñores
    0.48
    Activations Density 0.016%

    No Known Activations