© 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. 505
    Prev
    Next
    INDEX
    Explanations

    the word "name"

    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
    RegressionTest
    -0.65
    ]));
    -0.65
    دانشنامهٔ
    -0.62
     Официальный
    -0.56
    CompleteListener
    -0.54
     Kuba
    -0.53
    Tikang
    -0.53
     KGB
    -0.52
    tanleria
    -0.52
    unque
    -0.52
    POSITIVE LOGITS
    plate
    0.91
    plates
    0.81
    Surname
    0.77
     Names
    0.74
    akes
    0.68
    lessness
    0.68
     setName
    0.68
     getName
    0.66
     names
    0.66
    surname
    0.66
    Activations Density 0.430%

    No Known Activations