© 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. 22-RES-MATRYOSHKA-DC
    7. 1655
    Prev
    Next
    INDEX
    Explanations

    text about transcription factors.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     dAtA
    -0.73
    +:+
    -0.72
     jScrollPane
    -0.71
    ########.
    -0.66
     AdapterView
    -0.64
    팎
    -0.59
    پیوند
    -0.56
     BrowserModule
    -0.55
    alians
    -0.54
     Leaflet
    -0.54
    POSITIVE LOGITS
     transcription
    0.82
     transcriptional
    0.73
     binding
    0.73
     Transcription
    0.70
    Transcription
    0.69
    IVEREF
    0.63
    transcription
    0.63
     bind
    0.58
     TF
    0.57
    StoreMessageInfo
    0.57
    Activations Density 0.652%

    No Known Activations