© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13242
    Prev
    Next
    INDEX
    Explanations

    references to executing or running code

    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
    LLocation
    -0.59
    iexcl
    -0.57
    #+#
    -0.55
    конец
    -0.53
    RTDA
    -0.52
    ApiModelProperty
    -0.51
    APOLIS
    -0.50
    XtraGrid
    -0.50
    teiro
    -0.49
     mergeFrom
    -0.49
    POSITIVE LOGITS
    __':
    0.81
    __":
    0.74
    __":
    0.69
    \{\\
    0.64
    theoremstyle
    0.62
     Answered
    0.60
    __':
    0.59
    viewport
    0.59
    ecution
    0.58
     خارجية
    0.57
    Activations Density 0.087%

    No Known Activations