© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    uses words like 'that', 'such', 'in', 'with', 'for', plus forms of 'be' to find logical statements and mathematical proofs

    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
    LETE
    -0.57
    ാല
    -0.54
     primas
    -0.53
    calciatore
    -0.52
    technologies
    -0.52
    Хьажоргаш
    -0.51
    PointerException
    -0.50
    iella
    -0.50
    waran
    -0.49
    ATUM
    -0.48
    POSITIVE LOGITS
    styleType
    0.81
    CloseOperation
    0.77
    AnchorStyles
    0.76
    AndEndTag
    0.75
    HideFlags
    0.73
     Signalez
    0.69
     typelib
    0.67
    reactstrap
    0.65
     оригіналу
    0.64
     BoxFit
    0.64
    Activations Density 0.700%

    No Known Activations