© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 763
    Prev
    Next
    INDEX
    Explanations

    medical research papers in which cancer or cell death are discussed

    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
    ícil
    -0.76
    openzeppelin
    -0.64
    Filmografia
    -0.64
    minecraft
    -0.60
    URIComponent
    -0.60
    CompleteListener
    -0.59
    épendance
    -0.56
    ))))))))
    -0.54
    يكب
    -0.54
    mapStateToProps
    -0.53
    POSITIVE LOGITS
     also
    4.34
    also
    3.59
    Also
    3.30
     Also
    3.19
     también
    3.13
     também
    3.13
     также
    2.98
     également
    2.91
     juga
    2.88
     ALSO
    2.83
    Activations Density 4.145%

    No Known Activations