© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20653
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to American classic cars and their features

    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
    Personendaten
    -1.18
     Paglinawan
    -0.98
     estekak
    -0.81
     saites
    -0.80
     ExecuteAsync
    -0.76
    Хьажоргаш
    -0.76
     himo
    -0.75
    Rujuakan
    -0.75
     "..\..\..\
    -0.74
     Wikimedijinoj
    -0.73
    POSITIVE LOGITS
    WebControls
    0.48
    DllImport
    0.47
     natten
    0.46
    O
    0.41
     aspetta
    0.41
     circons
    0.40
     mesmas
    0.40
    enda
    0.39
     getchar
    0.38
     către
    0.37
    Activations Density 0.510%

    No Known Activations