© 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. 1078
    Prev
    Next
    INDEX
    Explanations

    the word "case", sometimes with surrounding words that indicate it's referencing a legal "case"

    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
     صوتيه
    -0.80
     Mercurio
    -0.79
    #+#
    -0.76
    Preparación
    -0.74
    υμ
    -0.74
    Память
    -0.69
     Colonna
    -0.69
     MonoBehaviour
    -0.68
    IconModule
    -0.68
     Monfieur
    -0.68
    POSITIVE LOGITS
     cases
    2.44
     case
    2.30
     Cases
    2.25
    case
    2.17
    Cases
    2.14
     Case
    2.11
    cases
    2.11
    CASE
    2.05
     CASE
    2.05
    Case
    1.98
    Activations Density 0.586%

    No Known Activations