© 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. 25734
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hide" or its variations indicating concealment or secrecy

    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
    __':
    -0.75
    WriteTagHelper
    -0.70
     PopupWindow
    -0.67
    Tikang
    -0.66
    WebRequest
    -0.66
    genstein
    -0.65
    MigrationBuilder
    -0.65
     consultato
    -0.63
     }}">
    -0.63
    WebVitals
    -0.62
    POSITIVE LOGITS
    hide
    0.97
     hide
    0.96
     hides
    0.94
     Hide
    0.93
    Hide
    0.92
    hiding
    0.91
     Hiding
    0.81
     hiding
    0.81
     hid
    0.76
    HIDE
    0.76
    Activations Density 0.019%

    No Known Activations