© 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. 6-RES-MATRYOSHKA-DC
    7. 182
    Prev
    Next
    INDEX
    Explanations

    seemingly random or nonsensical strings of characters, sometimes including version numbers or letters

    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
    y
    -1.84
    o
    -1.59
    e
    -1.36
    i
    -1.36
    ه
    -1.27
    t
    -1.26
    en
    -1.20
    er
    -1.18
    a
    -1.16
    s
    -1.16
    POSITIVE LOGITS
     Efq
    1.41
     Houſe
    1.33
     itſelf
    1.33
    Manbalar
    1.27
     myſelf
    1.24
     AssemblyCulture
    1.23
     COB
    1.20
    })*/
    1.20
     Rasp
    1.20
     Conſ
    1.20
    Activations Density 12.341%

    No Known Activations