© 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. 3-RES-MATRYOSHKA-DC
    7. 153
    Prev
    Next
    INDEX
    Explanations

    the effect of one thing on another

    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
    Bissau
    -0.76
    yně
    -0.61
    مصادر
    -0.60
    edicated
    -0.57
    FormsModule
    -0.56
    irah
    -0.56
    "><?=
    -0.56
     CIM
    -0.55
     vững
    -0.55
    craper
    -0.54
    POSITIVE LOGITS
     effect
    3.27
     effects
    3.16
     Effect
    3.11
     Effects
    3.03
    effect
    3.02
    Effect
    2.88
    Effects
    2.88
    effects
    2.88
     EFFECT
    2.83
     EFFECTS
    2.66
    Activations Density 1.034%

    No Known Activations