© 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. 1072
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving the number four

    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
     claim
    -1.18
    claim
    -1.08
     Claim
    -1.08
     claimed
    -1.07
     CLAIM
    -1.07
     claims
    -1.03
    claimed
    -1.02
     Claims
    -1.01
    claims
    -1.00
    Claims
    -0.98
    POSITIVE LOGITS
     Suppose
    3.31
    Suppose
    3.28
     suppose
    2.14
     supposes
    1.12
    Assume
    1.10
     supposing
    1.06
     Assume
    1.03
     suppos
    0.93
    Consider
    0.93
    sup
    0.90
    Activations Density 0.047%

    No Known Activations