© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1256
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "mbox" within complex mathematical and logical contexts

    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
    ModelSerializer
    -0.75
    ModelForm
    -0.71
    __':
    -0.66
    IMPORTED
    -0.66
    zard
    -0.65
    zu
    -0.61
    __":
    -0.60
    $
    -0.60
     pinulongan
    -0.59
     hilly
    -0.59
    POSITIVE LOGITS
    mbox
    3.45
    hbox
    1.54
    textrm
    1.25
    fbox
    1.02
    textnormal
    1.02
     itſelf
    0.81
    textbf
    0.75
     myſelf
    0.72
     fevere
    0.68
     raiſ
    0.67
    Activations Density 0.163%

    No Known Activations