© 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. 8873
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of terms related to user data privacy and security in online platforms

    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
    Reina
    -0.48
     w
    -0.44
    grafic
    -0.44
     balans
    -0.43
    SequentialGroup
    -0.43
     organes
    -0.43
    Derbyniad
    -0.42
     revenus
    -0.41
    isNull
    -0.40
     fichas
    -0.40
    POSITIVE LOGITS
    adaptiveStyles
    0.80
    IUrlHelper
    0.74
    Sklici
    0.66
    nodoc
    0.63
    Vidite
    0.63
     mergeFrom
    0.61
     pinulongan
    0.61
     createSlice
    0.60
    MigrationBuilder
    0.59
     createContext
    0.58
    Activations Density 0.006%

    No Known Activations