© 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. 931
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "in" followed by articles and other common words

    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
    umerable
    -0.52
    HasAnnotation
    -0.52
     his
    -0.46
    welche
    -0.44
    jsxFileName
    -0.44
    Total
    -0.43
    viste
    -0.43
    trui
    -0.42
    omi
    -0.41
    qtype
    -0.41
    POSITIVE LOGITS
     vivo
    0.75
     presence
    0.74
    ReusableCell
    0.72
    úly
    0.71
     Presence
    0.70
     aanwezig
    0.69
    ittoria
    0.68
     createContext
    0.68
    hibition
    0.66
    presence
    0.65
    Activations Density 0.697%

    No Known Activations