© 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. 582
    Prev
    Next
    INDEX
    Explanations

    phrases expressing difficulty or challenge

    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
     MonoBehaviour
    -0.69
    Xna
    -0.68
     Rossetti
    -0.68
     toluene
    -0.68
     Biôgrafia
    -0.66
    DockStyle
    -0.65
     numberWith
    -0.65
    OCCURRED
    -0.65
     vtk
    -0.63
    nitus
    -0.60
    POSITIVE LOGITS
     hard
    3.11
    Hard
    2.84
     Hard
    2.78
    hard
    2.78
     HARD
    2.72
    HARD
    2.61
     harder
    2.38
     hardest
    2.33
     difficult
    2.09
     harde
    2.08
    Activations Density 0.308%

    No Known Activations