© 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. 1965
    Prev
    Next
    INDEX
    Explanations

    the word "like"

    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
    zji
    -0.82
    oporosis
    -0.71
    ity
    -0.70
     ISNI
    -0.70
    ์ตูน
    -0.70
    idler
    -0.70
    TestingModule
    -0.69
    getDoctrine
    -0.68
    ίος
    -0.66
    iration
    -0.64
    POSITIVE LOGITS
     like
    2.41
    Like
    2.30
     Like
    2.27
     LIKE
    2.27
    like
    2.20
    LIKE
    2.06
     liek
    1.40
    likes
    1.31
    Likes
    1.30
     seperti
    1.27
    Activations Density 0.446%

    No Known Activations