© 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. 20848
    Prev
    Next
    INDEX
    Explanations

    references to SSL and HTTPS protocols

    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
    inosau
    -0.76
     McDowell
    -0.75
    yards
    -0.75
     Erskine
    -0.74
    )("
    -0.72
     Carne
    -0.69
    Dá
    -0.69
     TextAppearance
    -0.68
     okuyayım
    -0.68
     expressive
    -0.68
    POSITIVE LOGITS
     SSL
    1.41
    SSL
    1.33
     ssl
    1.15
    ssl
    1.13
    Ssl
    0.86
    DebuggerNonUser
    0.65
    StatusLabel
    0.61
     estatus
    0.55
    ConstraintMaker
    0.54
    resizingMask
    0.51
    Activations Density 0.004%

    No Known Activations