© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    terminology related to cell biology and cancer research

    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
    verhält
    -0.63
    DockStyle
    -0.61
     resourceCulture
    -0.60
     surla
    -0.60
    //
    -0.59
    softc
    -0.59
    ⓧ
    -0.58
     transfieras
    -0.57
    PostInfinity
    -0.56
     Husbandry
    -0.56
    POSITIVE LOGITS
     apoptosis
    0.86
     cell
    0.79
     apoptotic
    0.79
     Apoptosis
    0.74
    poptosis
    0.73
     death
    0.73
     mitotic
    0.73
     DNA
    0.72
    cell
    0.70
    poptotic
    0.68
    Activations Density 0.930%

    No Known Activations