© 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. 1987
    Prev
    Next
    INDEX
    Explanations

    sentences that describe something's function

    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
    abel
    -0.49
    voyez
    -0.47
     letz
    -0.46
     PyLong
    -0.45
     ritrov
    -0.44
     Rücken
    -0.43
     kali
    -0.43
     eccell
    -0.43
    lidos
    -0.42
     cser
    -0.42
    POSITIVE LOGITS
    extAlignment
    0.83
    Sucesor
    0.78
     autorytatywna
    0.75
     defaultstate
    0.73
     influencing
    0.72
    IBOutlet
    0.71
    ApiModelProperty
    0.71
    rungsseite
    0.71
     roles
    0.70
     disambiguazione
    0.70
    Activations Density 1.587%

    No Known Activations