© 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. 1052
    Prev
    Next
    INDEX
    Explanations

    references to the adverb "really" or similarly pronounced words

    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
     ​​
    -0.66
     eventually
    -0.62
     also
    -0.56
    prisma
    -0.53
    brauch
    -0.52
    ستار
    -0.51
    ExtendWith
    -0.51
    complexContent
    -0.49
    CIC
    -0.48
    conceito
    -0.48
    POSITIVE LOGITS
    ly
    4.06
    LY
    3.23
    ally
    2.56
    ALLY
    2.22
    ely
    2.17
    ingly
    2.17
    ELY
    2.14
    mente
    2.02
    ously
    2.00
    ably
    1.97
    Activations Density 0.867%

    No Known Activations