© 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. 22-RES-MATRYOSHKA-DC
    7. 2130
    Prev
    Next
    INDEX
    Explanations

    the word "personal" and words appearing near it

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    Tikang
    -0.68
    ImageContext
    -0.64
    BagLayout
    -0.59
     disponibilités
    -0.57
     precisamente
    -0.57
    IsMutable
    -0.53
     StringTokenizer
    -0.53
     absoluto
    -0.52
    xchange
    -0.51
     vastaan
    -0.51
    POSITIVE LOGITS
     Personal
    0.98
    Personal
    0.91
     personal
    0.89
     PERSONAL
    0.81
    personal
    0.79
    PERSONAL
    0.79
     prywat
    0.68
    ersonal
    0.65
     injury
    0.63
    getWriter
    0.63
    Activations Density 0.046%

    No Known Activations