© 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. 2-RES-MATRYOSHKA-DC
    7. 5804
    Prev
    Next
    INDEX
    Explanations

    references to scientific proof or evidence

    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
     proved
    -1.66
     prove
    -1.63
     Prove
    -1.42
     proves
    -1.41
     proven
    -1.41
    proved
    -1.36
    proven
    -1.30
     proving
    -1.30
    prove
    -1.27
    Proven
    -1.20
    POSITIVE LOGITS
    proof
    1.59
     proof
    1.49
    Proof
    1.45
     Proof
    1.38
    PROOF
    1.27
     PROOF
    1.26
     proofs
    1.16
    proofing
    1.00
     Proofs
    0.98
     proofing
    0.81
    Activations Density 0.012%

    No Known Activations