© 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. 19957
    Prev
    Next
    INDEX
    Explanations

    terms related to zooming in and out in visual contexts

    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
    setHeader
    -0.71
    ory
    -0.65
     mu
    -0.56
    licas
    -0.54
    mä
    -0.53
     Prä
    -0.53
    SizeMode
    -0.53
     Mu
    -0.52
    [\
    -0.51
    もの
    -0.50
    POSITIVE LOGITS
     zoom
    1.50
    zoom
    1.37
    ZOOM
    1.30
    Zoom
    1.29
     Zoom
    1.26
     ZOOM
    1.24
     zooming
    1.24
     zoomed
    1.15
     zoon
    1.05
    URLException
    1.03
    Activations Density 0.005%

    No Known Activations