© 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. 205
    Prev
    Next
    INDEX
    Explanations

    verbs associated with physical actions and movement

    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
    UnusedPrivate
    -0.63
    XmlAccessType
    -0.62
    setof
    -0.61
     muualla
    -0.57
     AttributeSet
    -0.55
    PreAuthorize
    -0.54
    djangoproject
    -0.54
    WriteTagHelper
    -0.53
    antMatchers
    -0.52
    DebuggerNonUser
    -0.51
    POSITIVE LOGITS
     into
    1.56
     down
    1.50
     up
    1.45
     back
    1.42
     out
    1.39
     away
    1.23
     forward
    1.20
     off
    1.18
     onto
    1.18
     INTO
    1.04
    Activations Density 2.017%

    No Known Activations