© 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. 0-RES-MATRYOSHKA-DC
    7. 11859
    Prev
    Next
    INDEX
    Explanations

    references to unconditional or absolute statements

    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
     kasarigan
    -0.87
    rungsseite
    -0.81
    resents
    -0.71
     ujednoznacz
    -0.68
     nakalista
    -0.67
     препратки
    -0.67
     />\
    -0.66
     ſmall
    -0.65
     onCancelled
    -0.64
    yargs
    -0.63
    POSITIVE LOGITS
     ArrayAdapter
    0.88
     unconditionally
    0.65
     Carp
    0.64
    asList
    0.62
     veil
    0.62
    anis
    0.60
    Carp
    0.60
     shroud
    0.60
    hase
    0.60
     unconditional
    0.59
    Activations Density 0.094%

    No Known Activations