© 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. 11711
    Prev
    Next
    INDEX
    Explanations

    references to specific technical standards, protocols, or code identifiers

    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
    κε
    -0.53
    LookAnd
    -0.51
    glLoadIdentity
    -0.51
    de
    -0.49
    องค์
    -0.48
    renderItem
    -0.47
    তি
    -0.46
    וויק
    -0.45
     Bra
    -0.45
    tabular
    -0.44
    POSITIVE LOGITS
    DE
    1.90
     DE
    1.00
    __(/*!
    0.72
    DEO
    0.70
     esternos
    0.69
    DEF
    0.67
    #+#
    0.66
    uxxxx
    0.66
    GTCX
    0.65
    WebMethod
    0.64
    Activations Density 0.002%

    No Known Activations