© 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. 6437
    Prev
    Next
    INDEX
    Explanations

    keywords related to DNA and cancer treatments

    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
     esternos
    -0.61
     esque
    -0.52
    providedIn
    -0.50
    Искәрмәләр
    -0.49
    setHorizontal
    -0.48
    Atsauces
    -0.47
    卒
    -0.46
    med
    -0.46
    NameInMap
    -0.45
    toBeTruthy
    -0.45
    POSITIVE LOGITS
     CascadeType
    0.74
    ształ
    0.65
    CppCodeGen
    0.64
    itename
    0.63
    ExtendWith
    0.63
     aikaa
    0.63
    haden
    0.62
    eseorang
    0.62
     diza
    0.60
    adpleegd
    0.59
    Activations Density 0.828%

    No Known Activations