© 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. 31087
    Prev
    Next
    INDEX
    Explanations

    instances of the word "landing" and its variations

    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
     Sche
    -0.64
    assertRaises
    -0.61
     Ebert
    -0.61
     GenerationType
    -0.60
     Muth
    -0.58
    ajuato
    -0.58
    yargs
    -0.56
    bür
    -0.56
    XmlAttribute
    -0.55
     Kopp
    -0.55
    POSITIVE LOGITS
     landings
    1.35
    Landing
    1.20
     Landing
    1.19
     landing
    1.16
     landed
    1.16
    landing
    1.09
     lander
    0.88
     ashore
    0.87
     ujednoznacz
    0.83
     LAND
    0.81
    Activations Density 0.004%

    No Known Activations