© 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. 629
    Prev
    Next
    INDEX
    Explanations

    statements of assumption or presumption

    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
     claims
    -1.06
     claim
    -0.92
     claimed
    -0.82
     CLAIMS
    -0.81
     Claim
    -0.81
    claims
    -0.80
     Claims
    -0.80
     CLAIM
    -0.76
    Claim
    -0.75
    claim
    -0.74
    POSITIVE LOGITS
     assume
    4.00
     assumption
    3.52
     assumed
    3.50
     assuming
    3.50
     assumes
    3.48
    assume
    3.39
    assumed
    3.06
     Assume
    3.02
     assumptions
    2.94
    assumption
    2.94
    Activations Density 0.075%

    No Known Activations