© 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. 1-RES-MATRYOSHKA-DC
    7. 129
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "make."

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynnwys
    -0.75
     Roskov
    -0.73
     FetchType
    -0.73
    AnchorStyles
    -0.73
    GenerationType
    -0.72
    Portail
    -0.71
    Personendaten
    -0.68
    TagMode
    -0.66
    hoeddwyd
    -0.66
     htons
    -0.63
    POSITIVE LOGITS
     make
    3.67
    make
    3.59
    Make
    3.50
     Make
    3.47
     made
    3.30
     MAKE
    3.23
     makes
    3.19
    MAKE
    3.19
     making
    3.14
    makes
    3.14
    Activations Density 0.451%

    No Known Activations