© 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. 296
    Prev
    Next
    INDEX
    Explanations

    the word "internal" or phrases that use "internal".

    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
    displayquote
    -0.78
     تضيفلها
    -0.65
    ]")]
    -0.65
     scythe
    -0.64
     zbo
    -0.59
    Tikang
    -0.59
    bigskip
    -0.58
     Pilgri
    -0.58
     wavelet
    -0.57
     @"";
    -0.57
    POSITIVE LOGITS
     inside
    1.96
     Inside
    1.84
    Inside
    1.79
    inside
    1.76
     INSIDE
    1.70
    INSIDE
    1.66
     within
    1.63
     Within
    1.61
    Within
    1.55
    within
    1.52
    Activations Density 1.831%

    No Known Activations