© 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. 24-RES-MATRYOSHKA-DC
    7. 1046
    Prev
    Next
    INDEX
    Explanations

    technical words, especially words ending in "tion", "ion", "al", or relating to aircraft and fluid dynamics.

    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.24.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.24.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
    ьаж
    -0.63
     CreateTagHelper
    -0.61
    むしろ
    -0.56
    onAttach
    -0.56
     AssemblyTitle
    -0.55
    labelledby
    -0.55
     مُعرِّف
    -0.55
    それにしても
    -0.55
    RTLU
    -0.54
    toggler
    -0.53
    POSITIVE LOGITS
     waardoor
    1.59
     allowing
    1.55
     causing
    1.51
     making
    1.48
     enabling
    1.45
     resulting
    1.38
     thereby
    1.36
     vilket
    1.33
     forcing
    1.32
    resulting
    1.31
    Activations Density 3.427%

    No Known Activations