© 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. 3-RES-MATRYOSHKA-DC
    7. 2647
    Prev
    Next
    INDEX
    Explanations

    capitalized letters, possibly followed by a few numbers or other capitalized letters, and is thus finding names or abbreviations

    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
     cipolla
    -0.60
     giustizia
    -0.59
    VersionUID
    -0.56
     démocr
    -0.52
     női
    -0.52
     combattre
    -0.51
     présidenti
    -0.50
     Indexed
    -0.50
     Fitur
    -0.50
     embaj
    -0.49
    POSITIVE LOGITS
     endfor
    0.74
    LookAnd
    0.69
    expandindo
    0.66
    }],
    0.65
     BoxFit
    0.64
    thenReturn
    0.63
     htmlFor
    0.63
    CopyWith
    0.62
    protoc
    0.62
    NameInMap
    0.61
    Activations Density 0.892%

    No Known Activations