© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14827
    Prev
    Next
    INDEX
    Explanations

    genetic alterations associated with copy number variations

    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
     FontWeight
    -0.54
    BASEPATH
    -0.50
    cdef
    -0.50
    testcase
    -0.48
    })();
    -0.48
     jep
    -0.48
    يتر
    -0.47
    nextInt
    -0.47
    pyrid
    -0.47
    anton
    -0.46
    POSITIVE LOGITS
    PN
    2.63
     PN
    1.76
    pn
    1.14
    AndEndTag
    0.71
    ContentAsync
    0.69
     Winaray
    0.68
    Personensuche
    0.66
    IsMutable
    0.63
     pn
    0.63
    ControllerAdvice
    0.60
    Activations Density 0.005%

    No Known Activations