© 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. 26806
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical compounds, particularly those involving "tetra" in their naming

    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
    GeneratedValue
    -0.81
    inergic
    -0.78
     мәкал
    -0.73
    ApiModelProperty
    -0.67
     Bion
    -0.65
    Guido
    -0.65
     Qiao
    -0.65
     Kome
    -0.64
     Rul
    -0.64
    kamp
    -0.63
    POSITIVE LOGITS
     Tet
    1.53
     tet
    1.52
    Tet
    1.39
     Tetra
    1.39
     tetra
    1.34
     TET
    1.25
    tetra
    1.24
    Tetra
    1.24
    TET
    1.04
     Tetris
    0.91
    Activations Density 0.005%

    No Known Activations