© 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. 25645
    Prev
    Next
    INDEX
    Explanations

    locations of trails and paths in relation to natural features or urban areas

    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
    ())->
    -0.57
    __":
    -0.52
    Reentrant
    -0.48
    $_['
    -0.47
     AssemblyVersion
    -0.46
     negozi
    -0.45
     IMDG
    -0.45
    EndTag
    -0.44
     sayin
    -0.44
    AutoScale
    -0.44
    POSITIVE LOGITS
    Биография
    0.64
     Roskov
    0.63
    MLLoader
    0.62
    KURZBESCHREIBUNG
    0.60
    expandindo
    0.60
    存于互联网档案馆
    0.59
    LabelTagHelper
    0.59
     CommonModule
    0.58
     BrowserModule
    0.57
    setVerticalGroup
    0.56
    Activations Density 0.003%

    No Known Activations