© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1488
    Prev
    Next
    INDEX
    Explanations

    the number 7 alone

    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
    er
    -1.05
    3
    -0.80
    ner
    -0.71
     Feld
    -0.71
    ar
    -0.70
     par
    -0.69
    ForUser
    -0.67
    erl
    -0.67
     three
    -0.64
    ди
    -0.64
    POSITIVE LOGITS
     Seventh
    1.80
     seventh
    1.69
    Seventh
    1.69
     SEVEN
    1.67
    7
    1.66
     SEVENTH
    1.56
     Seven
    1.54
    seventh
    1.53
    SEVEN
    1.48
     seventies
    1.45
    Activations Density 2.969%

    No Known Activations