© 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. 20170
    Prev
    Next
    INDEX
    Explanations

    references to objects and materials involved in physical altercations and everyday actions

    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
    
    -0.81
    IntoConstraints
    -0.75
     AttributeSet
    -0.74
    enumi
    -0.67
     IBOutlet
    -0.64
    GeneratedValue
    -0.63
    tagHelperRunner
    -0.63
    GrantedAuthority
    -0.63
    migrationBuilder
    -0.60
     FormControl
    -0.60
    POSITIVE LOGITS
     umum
    0.43
     dirig
    0.40
    édrale
    0.39
     cul
    0.38
    就能
    0.37
     resulting
    0.37
    PUBLIC
    0.36
    QRect
    0.36
    createTable
    0.36
     станови
    0.36
    Activations Density 0.105%

    No Known Activations