© 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. 278
    Prev
    Next
    INDEX
    Explanations

    the words "real" or "actual" and related concepts

    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
    fjspx
    -1.09
    StoryboardSegue
    -0.79
     pinulongan
    -0.78
    +#+#
    -0.77
    AddTagHelper
    -0.75
    #+#
    -0.75
    MLLoader
    -0.74
     Amigo
    -0.73
     मिले
    -0.73
    verwijspagina
    -0.73
    POSITIVE LOGITS
     real
    1.38
     REAL
    1.30
     actual
    1.27
    REAL
    1.23
     true
    1.21
    real
    1.17
     reales
    1.17
     Real
    1.15
     actually
    1.14
    Real
    1.14
    Activations Density 1.962%

    No Known Activations