© 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. 2320
    Prev
    Next
    INDEX
    Explanations

    code snippets and android-specific code.

    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
     OnInit
    -0.65
    ReusableCell
    -0.65
     esigenze
    -0.53
     useRef
    -0.52
    tagext
    -0.49
    画家
    -0.49
     Insee
    -0.48
    detectChanges
    -0.48
     displays
    -0.47
     IBOutlet
    -0.47
    POSITIVE LOGITS
     secondary
    0.75
     tertiary
    0.71
     Secondary
    0.68
    Primary
    0.65
     Primary
    0.64
     primary
    0.63
    secondary
    0.63
     Accent
    0.62
     shadow
    0.62
    енча
    0.61
    Activations Density 0.146%

    No Known Activations