© 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. 6516
    Prev
    Next
    INDEX
    Explanations

    occurrences of cryptographic hash algorithm identifiers

    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
    lach
    -0.68
     Lech
    -0.66
     Kirch
    -0.63
     Cruces
    -0.62
     Koch
    -0.62
     Duch
    -0.61
     madden
    -0.61
    verwijspagina
    -0.61
    gaard
    -0.60
     Andra
    -0.59
    POSITIVE LOGITS
     sha
    3.42
    sha
    3.41
    Sha
    3.41
     Sha
    3.36
     SHA
    2.53
    SHA
    2.31
     Shak
    1.86
     shave
    1.77
     shaker
    1.74
     Shapiro
    1.68
    Activations Density 0.093%

    No Known Activations