© 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. 3-RES-MATRYOSHKA-DC
    7. 2777
    Prev
    Next
    INDEX
    Explanations

    the command 'cd', which is used to change directories

    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
     referenties
    -0.51
    Jura
    -0.51
     luft
    -0.50
     jura
    -0.48
     condomínio
    -0.48
     casual
    -0.48
    casian
    -0.48
    vänt
    -0.47
    thorne
    -0.47
     trafik
    -0.47
    POSITIVE LOGITS
    cd
    2.22
     cd
    1.77
    CD
    1.67
    CDs
    1.60
     CD
    1.41
     CDs
    1.41
    Cd
    1.38
     Cd
    1.32
     cds
    1.26
    xcd
    1.11
    Activations Density 0.017%

    No Known Activations