© 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. 22-RES-MATRYOSHKA-DC
    7. 1434
    Prev
    Next
    INDEX
    Explanations

    text related to skiing, ski lifts or ski resorts

    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.22.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.22.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
    RectangleBorder
    -0.69
    esModule
    -0.60
    onAttach
    -0.59
     zebrafish
    -0.57
    XMLSchema
    -0.57
    VersionUID
    -0.56
     FixedUpdate
    -0.56
    MENAFN
    -0.56
    EditorBrowsable
    -0.54
     pregi
    -0.54
    POSITIVE LOGITS
     climbers
    1.19
     climbing
    1.19
     climber
    1.17
     mountaine
    1.16
     alpine
    1.08
     climb
    1.08
     Climbing
    1.05
     summit
    1.02
     climbs
    1.02
    climbing
    1.02
    Activations Density 0.856%

    No Known Activations