Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 15185
    Prev
    Next
    INDEX
    Explanations

    referenced components related to bounding boxes in image processing

    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
    ########.
    -0.73
     MainAxisSize
    -0.71
    UnusedPrivate
    -0.60
    verwijspagina
    -0.59
    WebServlet
    -0.56
    ReusableCell
    -0.56
     privées
    -0.54
    providedIn
    -0.53
     userSchema
    -0.52
    󠁣
    -0.52
    POSITIVE LOGITS
    ClientRect
    1.01
    makeConstraints
    0.98
     CGRectMake
    0.83
     CGRect
    0.76
    CGRectMake
    0.69
    LEncoder
    0.66
    AnchorStyles
    0.65
    CGRect
    0.64
    Bounds
    0.63
    initWithFrame
    0.62
    Activations Density 0.055%

    No Known Activations