© 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. 18-RES-MATRYOSHKA-DC
    7. 205
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns in the context of personal anecdotes or opinions

    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.18.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.18.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
    rungsseite
    -0.62
    >",
    -0.59
     pinulongan
    -0.58
     Familienname
    -0.54
    balleur
    -0.53
     disambiguazione
    -0.51
    queryInterface
    -0.51
    ברס
    -0.50
     препратки
    -0.50
     increased
    -0.49
    POSITIVE LOGITS
     neither
    1.77
    neither
    1.61
     não
    1.57
     none
    1.55
     nowhere
    1.50
     Neither
    1.49
     tidak
    1.47
    Neither
    1.41
     never
    1.40
     not
    1.39
    Activations Density 6.079%

    No Known Activations