© 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. 929
    Prev
    Next
    INDEX
    Explanations

    the word 'private' followed by a noun

    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
     cref
    -0.77
    indrome
    -0.74
     bezeichneter
    -0.71
     ThemeData
    -0.71
    =="
    -0.68
     onOptions
    -0.66
    GEBURTS
    -0.66
    theless
    -0.65
    torio
    -0.63
     Gunther
    -0.60
    POSITIVE LOGITS
     private
    2.11
    private
    2.05
     Private
    2.02
    Private
    1.99
    PRIVATE
    1.97
     PRIVATE
    1.88
     privada
    1.79
     privados
    1.67
     privado
    1.66
     privata
    1.66
    Activations Density 0.233%

    No Known Activations