© 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. 25692
    Prev
    Next
    INDEX
    Explanations

    mathematical notations or expressions

    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
     differently
    -0.48
    orte
    -0.47
    mag
    -0.45
    anto
    -0.41
    ốt
    -0.40
    –
    -0.40
    :
    -0.39
     March
    -0.38
    nen
    -0.38
    žky
    -0.38
    POSITIVE LOGITS
    RectangleBorder
    0.99
     виправивши
    0.96
     propOrder
    0.94
    InputBorder
    0.91
     lenker
    0.85
    MessageTagHelper
    0.85
     nahilalakip
    0.84
    WireFormatLite
    0.82
    TemporalType
    0.82
    UIControlState
    0.81
    Activations Density 0.015%

    No Known Activations