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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 29868
    Prev
    Next
    INDEX
    Explanations

    lines starting with an asterisk in license agreements or legal disclaimers

    oai_token-act-pair · gemini-2.0-flash
    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
    Personendaten
    -0.65
    %;">
    -0.59
    lidge
    -0.58
     }{@
    -0.57
    ANDUM
    -0.57
    }}=$
    -0.55
     consultato
    -0.54
     endblock
    -0.54
    MarshalTo
    -0.54
    \}_{
    -0.54
    POSITIVE LOGITS
    شهاد
    0.66
    expandindo
    0.66
    arithmic
    0.60
     Phoen
    0.59
     atheism
    0.59
     admixture
    0.58
     epistle
    0.57
     Camer
    0.55
     ligiloj
    0.55
     المعيارى
    0.55
    Activations Density 0.012%

    No Known Activations