© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 116
    Prev
    Next
    INDEX
    Explanations

    removal of restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.75
    ViewFeatures
    -0.71
    MLLoader
    -0.69
    writeFieldEnd
    -0.69
    andExpect
    -0.66
    ResumeLayout
    -0.66
     EconPapers
    -0.66
     quæ
    -0.65
     ويكيپيديا
    -0.65
    offsetof
    -0.64
    POSITIVE LOGITS
    loon
    0.58
     rotations
    0.45
     MainAxisSize
    0.44
     distinctions
    0.42
     marbles
    0.41
     restraints
    0.40
    Zeneca
    0.39
    Vorte
    0.38
     Générale
    0.38
     excavations
    0.38
    Activations Density 0.004%

    No Known Activations