© 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. 2-RES-MATRYOSHKA-DC
    7. 6372
    Prev
    Next
    INDEX
    Explanations

    expressions of confidence or affirmation

    oai_token-act-pair · gpt-4.1-nano
    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
    #+#
    -0.66
    }}
    -0.52
     betweenstory
    -0.49
     AssemblyCompany
    -0.47
    Ded
    -0.44
    </em>
    -0.44
    larak
    -0.44
    щу
    -0.43
     …
    -0.43
    ˈ
    -0.43
    POSITIVE LOGITS
    directly
    0.84
     right
    0.80
     directly
    0.79
     directa
    0.74
     Directly
    0.74
     přímo
    0.74
     OnInit
    0.74
    ientôt
    0.71
     Ανακτήθηκε
    0.71
    EXACT
    0.71
    Activations Density 0.032%

    No Known Activations