© 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. 1035
    Prev
    Next
    INDEX
    Explanations

    the word "allow" and closely related words like "permit".

    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
    /**
    -0.82
     AssemblyCompany
    -0.80
    »?
    -0.76
     risques
    -0.74
    énus
    -0.73
    Personensuche
    -0.72
    SessionFactory
    -0.71
     Ceinture
    -0.71
    @[+][
    -0.69
     précip
    -0.69
    POSITIVE LOGITS
     allow
    1.55
    ALLOW
    1.55
     allows
    1.51
     ALLOW
    1.51
     allowed
    1.50
     allowing
    1.48
    Allow
    1.45
     Allow
    1.44
     Allows
    1.43
     Allowing
    1.43
    Activations Density 0.406%

    No Known Activations